Deep Learning with TensorFlow

This module introduces advanced features of Keras including the Functional API and Subclassing API, along with creating custom layers and models. Students will learn to integrate Keras with TensorFlow 2.x for enhanced functionality and develop sophisticated neural network architectures.

This module focuses on developing advanced convolutional neural networks using Keras. Students will master data augmentation techniques, implement transfer learning with pre-trained models, and explore transpose convolution for complex computer vision tasks.

This module covers building and training Transformer models using Keras for sequential data tasks. Students will learn to develop Transformer-based models for text generation, time series prediction, and effectively manage sequential data using TensorFlow.

This module explores unsupervised learning techniques including building autoencoders, implementing diffusion models, and developing generative adversarial networks (GANs). Students will gain expertise in generative modeling and advanced unsupervised learning tasks.

This module teaches advanced Keras development techniques including custom training loops, hyperparameter tuning with Keras Tuner, and model optimization. Students will learn to create sophisticated training workflows and optimize model performance.

This module introduces reinforcement learning concepts and applications using Keras. Students will implement Q-Learning algorithms and develop deep Q-networks (DQNs) to tackle advanced reinforcement learning challenges.

This module provides hands-on project experience through fruit classification and waste product classification using transfer learning. Students will apply learned concepts in practical scenarios and complete peer-graded assignments.