Advanced Deep Learning and Computer Vision

Module 01 - RBM and DBNs & Variational AutoEncoder

1.1 Introduction rbm and autoencoders
1.2 Deploying rbm for deep neural networks, using rbm for collaborative filtering
1.3 Autoencoders features and applications of autoencoders.

Module 02 - Object Detection using Convolutional Neural Net

2.1 Constructing a convolutional neural network using TensorFlow
2.2 Convolutional, dense, and pooling layers of CNNs
2.3 Filtering images based on user queries

Module 03 - Generating images with Neural Style and Working with Deep Generative Models

3.1 Automated conversation bots leveraging
3.2 Generative model, and the sequence to sequence model (lstm).

Module 04 - Distributed & Parallel Computing for Deep Learning Models

4.1 Parallel Training
4.2 Distributed vs Parallel Computing
4.3 Distributed computing in Tensorflow
4.4 Introduction to tf.distribute
4.5 Distributed training across multiple CPUs
4.6 Distributed Training
4.7 Distributed training across multiple GPUs
4.8 Federated Learning
4.9 Parallel computing in Tensorflow

Module 05 - Reinforcement Learning

5.1 Mapping the human mind with deep neural networks (dnns)
5.2 Several building blocks of artificial neural networks (anns)
5.3 The architecture of dnn and its building blocks
5.4 Reinforcement learning in dnn concepts, various parameters, layers, and optimization algorithms in dnn, and activation functions.

Module 06 - Deploying Deep Learning Models and Beyond

6.1 Understanding model Persistence
6.2 Saving and Serializing Models in Keras
6.3 Restoring and loading saved models
6.4 Introduction to Tensorflow Serving
6.5 Tensorflow Serving Rest
6.6 Deploying deep learning models with Docker & Kubernetes
6.7 Tensorflow Serving Docker
6.8 Tensorflow Deployment Flask
6.9 Deploying deep learning models in Serverless Environments
6.10 Deploying Model to Sage Maker
6.11 Explain Tensorflow Lite Train and deploy a CNN model with TensorFlow