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 Deep Learning Essentials - Neural Networks & Applications. It covers the machine learning and deep learning as well as their applications in healthcare, finance, autonomous systems and more; the concept of optimization in neural networks, backpropagation algorithm, chain rule and variants of gradient descent; the deep learning frameworks, overfitting, underfitting and regularization; the convolutional networks for image processing and CNN architectures covering LeNet-5, AlexNet, VGGNet and ResNet; and the CNN from Scratch, transfer learning, object detection with YOLO and faster R-CNN. 

 

During this interactive course, participants will learn recurrent neural networks (RNNs), long short-term memory (LSTM) and gated recurrent units (GRU); the RNN for text generation, attention mechanisms and transformers; the preprocessing text for sentiment analysis, word embeddings, LSTM model for sentiment classification and evaluating model performance with precision and recall; the generative adversarial networks (GANs), autoencoders and variational autoencoders (VAEs) and deep reinforcement learning (DRL); the Q-learning and deep Q-networks (DQN), AI in gaming and robotics, model deployment and optimization; and the explainability, interpretability and advanced research trends in deep learning.