Deep Learning in TensorFlow

Deep Learning in TensorFlow [4 courses]

Learn how to use deep learning to make predictions using data.

• Course 1

  Introduction to Deep Learning in TensorFlow

  6h

  Develop deep learning models by training and evaluating neural networks with TensorFlow to solve complex prediction problems.

  Course Objectives ▾

  • Explain the major concepts and terminology used in deep learning
  • Perform data preprocessing and exploratory analysis to prepare data for modeling
  • Build and evaluate deep learning regression models using TensorFlow’s Sequential and Functional APIs in Keras
  • Build a deep neural network to predict listing gains of IPOs on the Indian market
• Course 2

  Sequence Models for Deep Learning

  6h

  Model sequential data by building and evaluating RNN, GRU, and LSTM architectures for time-series forecasting and sequence prediction tasks.

  Course Objectives ▾

  • Describe sequential neural network models
  • Determine when to use RNN, GRU, and LSTM
  • Implement a sequential model using a basic RNN
  • Implement a time series forecast model using LSTM and GRU
• Course 3

  Natural Language Processing for Deep Learning

  5h

  Process and model text data by applying NLP techniques such as tokenization, embeddings, sequence models, and transformers to build deep learning solutions.

  Course Objectives ▾

  • Process and explore text data
  • Visualize text data using a word cloud
  • Implement tokenization and word embeddings
  • Build sequence models
  • Build a transformer-based text classification model
• Course 4

  Convolutional Neural Networks for Deep Learning

  12h

  Design and refine convolutional neural network models for computer vision by training, regularizing, and fine-tuning CNN architectures on image data.

  Course Objectives ▾

  • Explain the basics of convolutional neural networks (CNNs)
  • Build and train a CNN for an image classification task
  • Implement regularization techniques
  • Fine-tune a CNN model using transfer learning