AI Courses
These AI courses teach concepts like neural networks, Large Language Models (LLMs), and deep learning using Python. You’ll build intelligent models to process information, generate content, and solve real-world problems.
AI Courses
These AI courses teach concepts like neural networks, Large Language Models (LLMs), and deep learning using Python. You’ll build intelligent models to process information, generate content, and solve real-world problems.
Showing 41 of 41 courses
- 38 courses 27 projects 154 hours 449K+
Data Scientist in Python Certificate Program
In this path, you'll develop key technical skills for data scientists, including object-oriented and functional programming with Python, along with libraries like scikit-learn, Matplotlib, NumPy, and pandas. You'll also learn web scraping, SQL queries, deep learning, machine learning, and predictive analysis. To help you stand out, you'll explore tools like the UNIX command line, Git, and GitHub for better collaboration. Best of all, you'll learn by doing - you'll write code and get feedback directly in the browser. You'll apply your skills to several guided projects involving realistic business scenarios to build your portfolio and prepare for your next interview.
Beginner Python SQLStart career path → - 30 courses 20 projects 183 hours 159K+
AI Engineer in Python
In this path, you'll build the technical skills AI engineers need, including Python programming, working with LLM APIs, and prompt engineering. You'll learn to build and deploy AI applications using FastAPI and Docker, then go deeper into machine learning, deep learning with PyTorch, embeddings, vector databases, and RAG systems. You'll also pick up essential tooling like the command line, Git, and virtual environments. Best of all, you'll learn by doing - you'll write code and get feedback directly in the browser. You'll apply your skills to several guided projects involving realistic business scenarios to build your portfolio and prepare for your next interview.
Beginner Python AI EngineeringStart career path → - 30 courses 14 projects 80 hours 125K+
Data Engineer
In this path, you'll master the mandatory technical skills for modern data engineering, including Python programming, distributed computing, containerization, and cloud deployment. You'll learn how to work with production databases like PostgreSQL, Snowflake, and MongoDB, process data at scale with PySpark, orchestrate workflows with Apache Airflow, and deploy containerized applications to cloud platforms using Docker and Kubernetes. Best of all, you'll learn by doing - you'll write code and get feedback directly in the browser. You'll apply your skills to several guided projects involving realistic business scenarios to build your portfolio and prepare for your next interview.
Beginner Python SQLStart career path → - 23 courses 18 projects 88 hours 93K+
Data Analyst in R
In this path, you'll learn the fundamentals of R and build upon them with more advanced skills. You'll learn how to use RStudio, applications and tools, tidyverse, DataFrames, tibbles, operators, expressions, and much more - as well as data visualization, graphs, plots, and charts. Best of all, you'll learn by doing - you'll write code and get feedback directly in the browser. You'll apply your skills to several guided projects involving realistic business scenarios to build your portfolio and prepare for your next interview.
Beginner R SQLStart career path → - 8 courses 3 projects 32 hours 24K+
Generative AI Fundamentals in Python
Gain the skills necessary for working with AI, from automating tasks to engaging with LLMs via API in Python, and progress to building AI-driven applications. This path is essential for professionals aiming to integrate AI into their toolkit.
Beginner Python Data ScienceStart skill path → - 7 courses 7 projects 25 hours 17K+
Machine Learning Using Python
In this path, you'll gain a strong understanding of supervised and unsupervised machine learning algorithms. You'll also learn some of the most important and used algorithms and techniques to build, customize, train, test and optimize your predictive models such as linear regression modeling, gradient descent, logistic regression modeling and decision tree and random forest modeling. Finally, you'll learn optimization techniques that will help you to improve efficiency and accuracy. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. You'll apply your skills to several guided projects with realistic business scenarios to build your portfolio and prepare for your next interview.
Intermediate Python Data ScienceStart skill path → - 4 courses 1 projects 17 hours 10K+
LLM Fundamentals in Python
Learn to work with large language models through APIs, prompt engineering, and advanced patterns like function calling and MCP. Then put your skills to work building interactive AI-powered web applications with Streamlit.
Intermediate Python AIStart skill path → -
Free
3 courses 0 hours 5.5K+
Zero to GPT
This course stars with the fundamentals - neural network architectures and training methods. Later in the course, we'll explore complex topics like transformers, GPU programming, and distributed training. You'll need to understand Python to take this course, including for loops, functions, and classes. The first part of this Dataquest path will teach you what you need. To get the most out of this course, go through each chapter sequentially. Read the lessons or watch the optional videos - they have the same information. Look through the implementations to solidify your understanding, and recreate them on your own.
Intermediate Data Science Data AnalysisStart skill path → - 4 courses 4 projects 23 hours 3.3K+
Deep Learning in TensorFlow
On this path, you'll learn all about deep learning, including how to build, train, and evaluate models with the TensorFlow framework. You'll then learn how to conduct forecasts on real data by applying sequential neural network models to time series forecasting. Next, you'll learn how to use TensorFlow tools and libraries to work on a range of NLP use cases, including text visualization, sentiment analysis models, and more. Finally, you'll learn how to apply convolutional neural networks (CNNs) to computer vision tasks so that you can teach computers to see and interpret digital images. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. You'll apply your skills to several guided projects with realistic business scenarios to build your portfolio and prepare for your next interview.
Intermediate TensorFlow Data ScienceStart skill path → - 2 courses 12 hours 59+
Data Literacy and AI Fundamentals
Build practical data literacy skills and learn how AI fits into everyday data work. This short skill path is designed for non-technical professionals who want to understand, explain, and work with data more confidently—and use AI as a helpful support tool without writing code.
Beginner Data Literacy Data CommunicationStart skill path → - 5 lessons 7 hours 15K+
Introduction to Supervised Machine Learning in Python
In this course, you'll learn how to develop a machine learning workflow for classification tasks using scikit-learn. You'll learn how to build and implement the k-nearest neighbors algorithm using pandas and scikit-learn. Finally, you'll learn to train, validate, and improve your machine learning model for better performance and accuracy using techniques like tuning hyperparameters. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your new skills to complete a project to predict heart disease.
Intermediate Python Machine LearningStart course → - 3 lessons 2 hours 9.8K+
Calculus For Machine Learning
Calculus is one of the core mathematical concepts behind machine learning, and enables us to understand the inner workings of different machine learning algorithms. It plays an important role in the building, training, and optimizing machine learning algorithms. In this course, you'll learn to work with linear and nonlinear functions, including decomposing a linear equation into slope and y-intercept or defining slope. You'll also learn to use limits, including representing slope using limits, defining defined and undefined limits, and computing limits using SymPy. Finally, you'll identify extreme points in a nonlinear function and compute the derivative of a nonlinear function. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser.
Intermediate Calculus Machine LearningStart course → - 5 lessons 4 hours 9.4K+
Introduction to Python Programming
This interactive Python course for beginners develops fundamental web development skills to help you begin your journey to become a successful developer. In this course, you'll learn to do basic arithmetic; write code using Python syntax; work with different types of data; and perform basic Python operations such as working with variables, processing numerical and text data, and manipulating lists. Best of all, you'll learn by doing - you'll write code and get feedback directly in the browser.
Beginner Python Data ScienceStart course → - 4 lessons 2 hours 8.8K+
Linear Algebra For Machine Learning
Linear Algebra is a key branch of mathematics that is concerned with vectors, matrices, planes, and lines, and it helps to build blocks of machine learning algorithms. In this course, you'll learn how to define linear systems using linear algebra, how to represent a problem as a linear system, and how to solve linear systems by elimination. You'll learn how to define vectors using geometry, as well as how to perform vector operations and identify the link between linear combinations and solutions to linear systems. You'll also learn how to perform matrix operations in NumPy, how to define the matrix inverse and transpose, and how to solve the matrix inverse in higher dimensions. Finally, you'll learn to identify the different solution sets to linear systems and define homogeneous and nonhomogeneous systems. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser.
Intermediate Linear Algebra Machine LearningStart course → -
Free
3 lessons 2 hours 7.1K+
AI Chatbots: Harnessing the Power of Large Language Models with Chandra
Artificial Intelligence is redefining the landscape of technology and communication. In this course, you'll gain a foundational understanding of AI, machine learning, deep learning, natural language processing, and chatbots. Discover how to craft effective prompts and interact with chatbots like Chandra to maximize their potential in educational, work, and personal projects. By the end of this course, you'll have hands-on experience with Chandra and be inspired to explore further into AI and data science.
Beginner AI LLMsStart course → -
Free
3 lessons 1 hours 5.4K+
Neural Network Fundamentals
The course has several objectives. First, you will learn what a GPT model is (Generative Pre-trained Transformer) and how it operates. Additionally, the course will help you refresh your knowledge of linear algebra and calculus concepts that are crucial for deep learning. You'll learn how to manipulate matrices, perform vector calculus, and solve optimization problems. Finally, you will learn how gradient descent is used in deep learning. You'll learn how to train a linear regression model using gradient descent, and you'll learn how gradient descent is used to optimize neural network parameters. You'll also gain practical experience by implementing gradient descent algorithms from scratch using Python. By the end of this course, you'll have a solid understanding of the fundamental concepts of deep learning. You'll be well-prepared to continue your deep learning journey and move on to more advanced topics such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), leading up to training your own GPT model.
Intermediate Neural Networks Deep LearningStart course → - 5 lessons 5 hours 3.8K+
Introduction to Unsupervised Machine Learning in Python
In this course, you'll learn the fundamentals of the k-means algorithm and how to use it to build a model to segment data. You'll also learn to work with clusters with activities such as finding the optimal number of clusters, creating new clusters using the k-means algorithm in scikit-learn, and interpreting the results from a k-means model. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your new skills to complete a project to perform a credit card customer segmentation.
Intermediate Python Machine LearningStart course → - 5 lessons 4 hours 3.7K+
Linear Regression Modeling in Python
Linear regression shows us how we can use data to predict the value of an outcome. This course covers the structure of a linear regression model, how to interpret it, how to determine if a model is appropriate, and how to use the model to predict values of new data. In this course, you'll learn to create single and multiple linear regressions, identify the different types of predictors, and identify a cost function for linear regression. You'll also learn how to interpret regression parameters, how to check linear regression fit, and how to apply linear regression models. You will use tools such as scikit-learn, statsmodels, pandas, NumPy and matplotlib. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your new skills to complete a project to predict insurance costs.
Intermediate Python Linear RegressionStart course → - 5 lessons 6 hours 3.4K+
Decision Tree and Random Forest Modeling in Python
Decision trees are known in the machine learning world for a particularly distinctive characteristic: their visualizations are easier to understand compared to other machine learning models, and for this reason, they are very suitable for explaining insights to non-technical audiences. In this course, you'll learn the foundations of Decision Trees including identifying the key components of trees, interpreting them, classifying new observations using decision trees and calculating optimal thresholds for both classification and regression trees. You'll also learn how to build and visualize decision trees by adapting a real-life dataset to train tree models, selecting the appropriate scikit-learn tools to build your model, and training, testing and visualizing decision trees. You'll be able to evaluate and optimize trees for better performance including activities such as establishing the optimal depth for a decision tree, using Prune decision trees to avoid overfitting, or manipulating sample distribution in nodes and leaves. Finally, you'll learn how to apply the cross validation and ensemble techniques for decision trees. You'll identify the differences between decision trees and random forest models, develop and customize random forest models and optimize the parameters of random forest. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your new skills in a project to predict employee productivity with tree models
Intermediate Python Tree ModelsStart course → - 6 lessons 2 hours 3.2K+
Linear Regression Modeling in R
In this course, you'll learn how and when to use linear regression models to make predictions. You'll learn how to build linear regression models, how to interpret their output, and how to assess model accuracy. You'll also explore the limitations of linear regression models when data isn't linear. Finally, you'll learn to use programming tools to fit and visualize many linear regression models at once. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll complete a project to practice your skills with a subset of condominium sales data from all five boroughs of New York City.
Intermediate R Linear RegressionStart course → - 4 lessons 3 hours 2.9K+
Gradient Descent Modeling in Python
Gradient descent is one of the most commonly used optimization algorithms to train machine learning models, such as linear regression models, logistic regression, or even neural networks. It finds the minimum of any convex function by gradually converging toward it. In this course, you'll learn the fundamentals of gradient descent and how to implement this algorithm in Python. You'll learn the difference between gradient descent and stochastic gradient descent, as well as how to use stochastic gradient descent for logistic regression. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your new skills in a project to optimize a stochastic gradient descent algorithm on linear regression.
Intermediate Python Gradient DescentStart course → - 6 lessons 3 hours 2.9K+
Optimizing Machine Learning Models in Python
The amount of data and the complexity of machine learning models have grown exponentially which led to the development of additional methods and techniques to improve accuracy of predictive models. In this course, you will learn how to best select a model. You'll get a strong understanding of cross-validation in the machine learning workflow and how to use k-fold and LOOCV cross-validation techniques to check performance. Then, you'll learn how to use regularization in machine learning including activities such as using regularized versions of linear regression, identifying the difference between ridge and LASSO regression or standardizing the features using helper functions in scikit-learn. Finally, you'll go beyond linear models by implementing polynomial regression in scikit-learn, defining piecewise functions and splines, implementing regression splines in scikit-learn and establishing best practices concerning splines Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your new skills in a project to optimize a predictive model.
Intermediate Python Machine LearningStart course → - 5 lessons 3 hours 2.9K+
Logistic Regression Modeling in Python
Logistic regression and linear regression are very similar, but the two have slightly different objectives. In linear regression, we try to predict losses in insurance claims. In logistic regression, we're trying to predict categorical outcomes, otherwise known as classification. In other terms, logistic regression is the classification-based equivalent of linear regression. In this course, you'll learn the logistic regression method. You'll learn how to interpret regression parameters, how to evaluate logistic regression models, and how to apply them. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll combine your skills to complete a project to classify heart diseases.
Intermediate Python Logistic RegressionStart course → - 6 lessons 6 hours 2.5K+
Introduction to Deep Learning in TensorFlow
Deep learning is a discipline in artificial intelligence that has recently garnered a lot of interest. It's used to solve complex problems in various fields such as computer vision, natural language processing, robotics, and others that might be difficult to solve using traditional machine learning methods. In this course, you'll start with the fundamentals of deep learning, and you'll explore the TensorFlow library. Then, you'll learn to build, train, and evaluate deep learning regression and classification models using the TensorFlow framework. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll apply your new skills to a project to build a deep neural network model that can predict the listing gains of IPOs on the Indian market.
Intermediate TensorFlow Deep LearningStart course → - 6 lessons 1 hours 2.4K+
Introduction to Machine Learning in R
In this course, you'll learn key concepts such as KNN Algorithms (K-Nearest Neighbors), error metrics including the Mean Squared Error and the Root Mean Squared Error and caret, a machine learning library for the R programming language. You'll learn how to optimize machine learning algorithms for better accuracy and performance of trained models using hyperparameter optimization. You'll then dig into performing rigorous model testing using k-fold cross-validation. As you learn these new skills, you'll be working with AirBnB prices data from Washington D.C. to predict the optimal price for generating profit from a Washington D.C. home rental. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll complete a project to predict car prices using the K-Nearest Neighbors algorithm. This project is a chance for you to combine the skills you learned in this course and practice a machine learning workflow.
Advanced R Machine LearningStart course → - 4 lessons 6 hours 2.4K+
Prompting Large Language Models in Python
In this course, you'll gain in-depth insights into the practical applications of large language models. Starting with the fundamentals of the OpenAI Chat Completions API, you'll journey through creating dynamic AI-driven interactions. You'll learn to maintain context in conversations by managing history effectively and use prompt engineering techniques to steer AI responses. Additionally, the course covers efficient token usage in scripting, ensuring your applications run smoothly. The blend of theoretical knowledge and hands-on practice in this course positions you at the forefront of AI interaction technology.
Intermediate Python LLMsStart course → - 6 lessons 12 hours 2.2K+
Intermediate Python for AI Engineering
This course focuses on intermediate Python skills needed for development and working with AI. Throughout the course, you'll dive into object-oriented programming tailored for applications, grasp the fundamentals of decorators, and work with regular expressions, list comprehensions, and lambda functions. Elevate the functionality and efficiency of your projects, and confidently tackle user input errors and typical programming challenges. You'll put it all together in a guided project where you build a garden simulator text-based game.
Beginner Python AIStart course → - 4 lessons 4 hours 2.0K+
Designing Dynamic Python Applications with Streamlit
In this course, you'll learn the ins and outs of Streamlit. You'll begin by grasping the fundamentals of the Streamlit framework, followed by designing user interfaces with widgets like sliders, buttons, and text input. The course then moves into managing state within a Streamlit app and culminates with the integration of an LLM API for dynamic chatbot responses. The hands-on exercises and real-world scenarios provide an immersive learning experience, ensuring you gain practical skills and knowledge. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. Engage in realistic business scenarios, from a customer service app for a coffee startup to an AI chatbot for a tech firm, building your portfolio and prepping for your next career move all while learning a new skill.
Intermediate Python StreamlitStart course → -
Free
3 lessons 0 hours 662+
Network Architectures
This is the second course in a series of courses that will take you from no knowledge of deep learning to training your own GPT model (Generative Pre-trained Transformer). You'll gain a deeper understanding of different network architectures, and you'll learn to build neural networks from scratch using Python and to make predictions for both categorical and sequential outcomes. After you have completed this course, you will understand different neural network architectures. You will be able to build a dense neural network from scratch using Python, train a neural network on a classification task, and predict sequence data using recurrent neural networks. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser!
Intermediate Deep Learning Neural NetworksStart course → - 6 lessons 5 hours 603+
Natural Language Processing for Deep Learning
First, you'll explore the concepts and terms necessary for working with sequential models in TensorFlow. You'll discover recurrent neural networks (RNN) and how they compare with convolutional neural networks (CNNs), as well as some of the most common RNN applications. Then, you'll learn how to build, train, evaluate, and improve a basic RNN to predict song popularity using regression. You'll also learn to use Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) techniques to improve model performance. You'll implement these to predict the sentiment of the review (good or bad) on a dataset of IMDB reviews. Next, you'll combine convolutional neural networks with sequential models to add a convolutional layer to your LSTM model and compare its predictive performance before and after on a dataset of IMDB reviews, predicting sentiment. Finally, you'll optimize the tools already used for time-series forecasting on a dataset of movie ticket sales to prepare you for the guided project. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll apply your new skills to a project to build a model to better forecast how the S&P 500 futures index will move based on its behavior over the past several years.
Intermediate Deep Learning NLPStart course → - 6 lessons 6 hours 572+
Sequence Models for Deep Learning
First, you'll explore the concepts and terms necessary for working with sequential models in TensorFlow. You'll discover recurrent neural networks (RNN) and how they compare with convolutional neural networks (CNNs), as well as some of the most common RNN applications. Then, you'll learn how to build, train, evaluate, and improve a basic RNN to predict song popularity using regression. You'll also learn to use Gated Recurrent Units (GRU) and Long Short-Term Memory (LSTM) techniques to improve model performance. You'll implement these to predict the sentiment of the review (good or bad) on a dataset of IMDB reviews. Next, you'll combine convolutional neural networks with sequential models to add a convolutional layer to your LSTM model and compare its predictive performance before and after on a dataset of IMDB reviews, predicting sentiment. Finally, you'll optimize the tools already used for time-series forecasting on a dataset of movie ticket sales to prepare you for the guided project. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll apply your new skills to a project to build a model to better forecast how the S&P 500 futures index will move based on its behavior over the past several years.
Intermediate Deep Learning Sequence ModelingStart course → - 6 lessons 12 hours 539+
Introduction to Deep Learning in PyTorch
Deep learning is a discipline in artificial intelligence that has recently garnered a lot of interest. It's used to solve complex problems in various fields such as computer vision, natural language processing, robotics, and others that might be difficult to solve using traditional machine learning methods. In this course, you'll start with the fundamentals of deep learning and PyTorch tensors, then advance to professional-grade techniques including proper data methodology, advanced regularization, and comprehensive evaluation practices. You'll learn to build robust models that generalize well to new data using batch normalization, dropout, and early stopping. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll apply your advanced skills to build a regularized deep neural network that predicts IPO listing gains with sophisticated evaluation techniques.
Advanced Python Machine LearningStart course → - 6 lessons 12 hours 522+
Convolutional Neural Networks for Deep Learning
First, you'll learn the relevance of CNN in the field of computer vision, and you'll implement both basic and complex CNN for multi-class classification tasks in TensorFlow. You'll then advance to understanding how a CNN model learns different features across its layers and attempts to improve the model's performance. You'll learn different regularization techniques to tackle overfitting when building deep learning models in TensorFlow. Next, you'll see the importance of complicated models like ResNet for computer vision tasks, and you'll implement a ResNet-based, pre-trained model on advanced CNN architecture. Finally, you'll learn how to use previously trained models for other similar tasks on a different dataset than the original model was trained on. Best of all, you'll learn by doing - you'll practice and get feedback directly in the browser. At the end of the course, you'll apply your new skills to a project to create a computer vision model that can detect if a patient has pneumonia using an X-ray scan.
Advanced Deep Learning Computer VisionStart course → - 4 lessons 3 hours 417+
Analyzing Large Datasets in Spark
Master Apache Spark, the leading framework for big data processing. This hands-on course teaches you to work with Spark's core data structures - RDDs and DataFrames - while understanding the distributed architecture that makes Spark 10-100x faster than traditional tools. You'll analyze real datasets including US Census data and Daily Show guests, learning when to use RDDs for custom transformations, DataFrames for optimized operations, and Spark SQL for complex queries. By the end, you'll confidently process datasets that don't fit on a single machine.
Intermediate Data Science Data AnalysisStart course → -
Free
2 lessons 0 hours 397+
Optimizing Network Parameters
In this course, you'll dive into the world of deep learning by gaining a deeper understanding of backpropagation and building a simple deep learning framework from scratch. As part of your journey, you'll learn to optimize network parameters and employ regularization techniques to improve your models, creating a strong foundation in core deep learning concepts. The course will also explore the essential role of optimizers in adjusting neural network parameters. You'll delve into gradient descent and learn about batch size, learning rate schedules, weight decay, and momentum. Additionally, you'll discover the popular Adam optimizer, which extends the idea of momentum, and learn how to optimize hyperparameters for neural networks while monitoring and comparing their performance. By the end of this course, you'll have a comprehensive understanding of fundamental deep learning concepts and be well-equipped to continue your deep learning journey.
Intermediate Deep Learning OptimizationStart course → - 3 lessons 6 hours 202+
Introduction to Retrieval-Augmented Generation (RAG)
Retrieval-Augmented Generation (RAG) lets you build AI systems that answer questions grounded in real documents rather than relying on model memory alone. In this course, you'll build a RAG pipeline from scratch, improve retrieval with techniques like query expansion and reranking, and learn to diagnose common failure modes. The focus is on practical implementation: understanding how each stage of the pipeline works and how to make the system reliable.
Intermediate RAG LLMsStart course → - 3 lessons 6 hours 148+
Understanding Embeddings
Embeddings transform text into numerical vectors that capture semantic meaning, enabling AI systems to understand context beyond simple keyword matching. In this course, you'll learn how to generate embeddings using both open-source models and APIs, visualize them in reduced dimensions, measure similarity between vectors, and build semantic search systems that power modern AI applications.
Intermediate Embeddings Semantic SearchStart course → - 3 lessons 6 hours 137+
Tool Use with LLMs in Python
Move from experimental prompts to reliable LLM systems. This course teaches you the engineering patterns that make LLM interactions dependable: structured outputs with validation, function calling for tool integration, and the Model Context Protocol for reusable tool servers. You'll learn how to handle messy LLM outputs, build agentic loops that execute multi-step tasks, and create maintainable components that work consistently.
Intermediate LLM Systems Function CallingStart course → - 6 lessons 12 hours 92+
Vector Databases and Search
Vector databases enable semantic search at scale by using approximate nearest neighbor algorithms instead of brute-force comparison. In this course, you'll learn to build production-ready vector search systems using ChromaDB, implement document chunking and metadata filtering strategies, compare production databases, apply semantic caching patterns, and create a complete knowledge base search system combining hybrid search and performance optimization.
Intermediate Vector Databases Semantic SearchStart course → - 4 lessons 8 hours 78+
Deep Learning Applications in PyTorch
Deep learning is applied differently depending on the type of problem you're solving. In this course, you'll explore how PyTorch is used across key application areas including sequence models, natural language processing, and computer vision. Rather than focusing on deep theory or production optimization, this course emphasizes understanding model structures, data representations, and common patterns so you can recognize how deep learning solutions are built in practice.
Advanced PyTorch Deep LearningStart course → - 3 lessons 6 hours 50+
Using AI to Work with Data
AI is becoming a common tool for working with data, even for non-technical roles. In this course, you'll learn how to use AI tools to explore data, improve communication, and support everyday data tasks—without writing code or building models. You'll gain practical skills for prompting AI effectively and understanding its strengths and limitations in real data work.
Beginner AI Literacy Data CommunicationStart course →
Related resources on AI
- Article
10 Generative AI Skills You Need to Succeed
The ability to use generative AI effectively is becoming a critical skill for professionals looking to advance their careers. This blog post provides a practical guide to using generative AI to succeed in the modern workplace.
16 min read View article → - Article
Why Should You Learn Generative AI Skills?
Generative AI is reshaping industries and creating a need for expertise in this cutting-edge field. Dataquest’s Generative AI Fundamentals in Python skill path equips you to succeed in a job market that's increasingly driven by innovation and efficiency.
11 min read View article → - Article
What is Generative AI and How Is It Being Used?
Have you ever paused to consider that Generative AI is revolutionizing how we create content and interact with technology? Its transformative power extends beyond mere technological innovation, directly impacting content creation and user experiences.
12 min read View article →
Learn AI by building projects
-
Free
Project
Developing a Dynamic AI Chatbot
For this project, you’ll become a developer at a tech company, using Python and the OpenAI API to create an engaging AI chatbot. You’ll gain skills in conversation management, persona creation, and token handling as you build a chatbot that adapts to different platforms.
11 steps Start project → -
Free
Project
Garden Simulator Text Based Game
For this project, you’ll step into the role of a Python game developer to create an interactive text-based “Garden Simulator” using object-oriented programming, error handling, and randomness.
11 steps Start project → -
Free
Project
Build a Food Ordering App
For this project, you’ll become a restaurant owner building a Python food ordering app. You’ll use dictionaries, loops, and functions to create an interactive system for viewing menus, modifying carts, and placing orders.
12 steps Start project →
Frequently Asked Questions
How do you choose the right AI course for your goals?
Pick an AI course based on what you want to achieve. If you want to use AI tools like prompt engineering, pick a course focused on applications. If you want to build AI systems, choose one that teaches Python, machine learning, and neural networks.
Dataquest covers both, offering hands-on coding with Python, machine learning basics, and large language model workflows.
What are the best AI courses online?
The best AI courses focus on practical coding, not just theory. Look for courses that teach core AI concepts and let you apply them to real problems.
Some courses show how to use AI tools like ChatGPT, while others teach how to build AI systems from scratch. Dataquest emphasizes building AI systems, letting you write and run code in your browser so you truly understand how AI works.
How much do AI courses cost?
Costs vary widely, from free introductory courses to monthly subscriptions on learning platforms to university programs costing thousands.
Dataquest offers an affordable subscription with full access to all data science, analytics, engineering, and AI courses. It also includes free lessons and a 14-day money-back guarantee, so you can start learning risk-free.
Will you get a certificate, and does it help you stand out?
Yes, you earn a certificate after completing a course, but certificates alone rarely land AI roles. What matters most is a portfolio showing real projects and models you’ve built. Dataquest helps you create these practical projects as you learn, so you gain skills that truly stand out.
What is AI?
Artificial Intelligence (AI) is the creation of systems that can perform tasks requiring human intelligence, such as analyzing data, recognizing patterns, and making decisions. AI engineers build these systems using algorithms, models, and data, including AI agents that automate workflows or respond to inputs.
Dataquest teaches the practical side of AI with Python, letting you build and deploy real AI solutions through hands-on coding, without relying on theory or buzzwords.
What are generative AI models?
Generative AI models are systems that create new content rather than only analyzing data. They can generate text, images, or code based on patterns learned from training data.
Many generative AI models rely on natural language processing (NLP) and are built as large language models (LLMs). These models generate human-like text by predicting what comes next in a sequence of words.
What tools are commonly used in AI?
Common AI tools include Python, PyTorch, TensorFlow, the OpenAI API, and Hugging Face. Dataquest gives you hands-on experience with these industry-standard libraries.
Are AI skills still in demand?
Yes, AI skills are still in high demand. Many companies are adopting AI across products and internal systems and need people who understand how these systems work.
Learning AI helps you move beyond simply using AI tools. You learn how to build, evaluate, and optimize models, which allows you to work directly with AI systems.
What jobs can you get with AI skills?
AI skills can lead to several technical and hybrid roles, including:
- Machine Learning Engineer
- AI Specialist
- Data Scientist
- NLP Engineer
- AI Product Manager
These roles usually require strong foundations in Python and machine learning, which Dataquest focuses on across its AI courses.
What qualifications do you need for AI?
You do not need formal qualifications to start working in AI, but you do need core technical skills. Most AI roles require Python, basic machine learning, and computer science fundamentals. These skills are commonly built through courses and hands-on projects rather than a specific degree.
Is AI hard to learn?
AI can be harder to learn than some other tech skills because it builds on computer science concepts such as math, algorithms, and data processing. However, many people learn AI successfully by building strong AI foundations in Python and basic machine learning.
Dataquest focuses on essential AI skills through hands-on practice, helping you understand how AI systems work rather than treating them as black boxes.
How long will it take to become job-ready in AI?
AI is an advanced field. Most learners need six to twelve months or more to build a solid foundation, often starting with data science and machine learning basics. Dataquest supports learners throughout this process with structured learning paths.
What’s the 30% rule in AI?
The 30% rule in AI is an informal guideline used in responsible AI. It suggests that humans should handle around 30% of a task, especially the creative or judgment-based parts, while AI handles repetitive work.
This balance is an important idea in AI ethics. Many AI roles focus on building systems that support human work rather than fully replacing it.
Join 1M+ data learners on Dataquest.
- 1
Create a free account
- 2
Choose a learning path
- 3
Complete exercises and projects
- 4
Advance your career