COURSE OVERVIEW

This practical and highly-interactive course includes real-life case studies and exercises where participants will be engaged in a series of interactive small groups and class workshops. 

This course is designed to provide participants with a detailed and up-to-date overview of Neural Networks and Deep Learning. It covers the AI, machine learning and deep learning; the basics of artificial neural networks (ANN); the fundamentals of deep learning, neural network architecture, cost function and optimization in neural networks; setting up deep learning environment; the backpropagation and gradient descent including hyperparameter tuning and regularization; the activation functions and their role and evaluating neural networks; and the data preprocessing for neural networks. 

 

Further, the course will also discuss the implementation of first neural network with TensorFlow/PyTorch and convolutional neural networks (CNNs); the convolutional layers, pooling and fully connected layers; implementing CNNs with TensorFlow and PyTorch; how transfer learning speeds up training; using pre-trained models from TensorFlow/Keras; and the image data augmentation techniques. 

During this interactive course, participants will learn the overfitting in CNNs and how to handle it and computational efficiency in deep networks; the batch normalization for stabilizing training and hardware acceleration (GPUs & TPUs); the recurrent neural networks (RNNs) and time-series data, long short-term memory (LSTM), gated recurrent units (GRU), word embeddings and Word2Vec; the natural language processing (NLP) with deep learning, attention mechanism and transformers; the natural language processing (NLP) applications; the generative adversarial networks (GANs); the autoencoders for anomaly detection, reinforcement learning and deep Q-networks (DQN); the distributed training with TensorFlow and model deployment using TensorFlow serving; the cloud-based deep learning and optimization techniques for large-scale networks; the ethical considerations in AI and deep learning; and building and deploying a deep learning model.