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 Tensorflow & Keras. It covers the deep learning and setting up TensorFlow and Keras environment; the basics of tensors and tensor operations and building neural network with Keras API; the data handling in TensorFlow and TensorBoard for model visualization; the backpropagation and gradient descent and customizing training with callbacks; handling overfitting and underfitting; the model evaluation and hyperparameter tuning; and using pretrained models for transfer learning. 

 

Further, the course will also discuss the performance with distributed training, convolutional neural networks (CNNs) and building a CNN from scratch using Keras; the image augmentation and data preprocessing, transfer learning with CNNs and object detection and segmentation in TensorFlow; deploying CNN models for real-world applications, recurrent neural networks (RNNs) and building RNNs with Keras; and the word embeddings, text representation, sentiment analysis and text classification. 

 

 

During this interactive course, participants will learn the transformer models in TensorFlow and chatbots with TensorFlow; the generative adversarial networks (GANs), autoencoders for anomaly detection and reinforcement learning with TensorFlow; converting models to TensorFlow Lite (TFLite) and deploying models using TensorFlow.js; the TensorFlow serving and using Docker and Kubernetes for AI applications; using TensorFlow on Google Cloud; and deploying models with AWS SageMaker.