Neural Networks and Deep Learning Training
Overview
This course explains Neural Networks and Deep Learning. At the end of the course, participants will be able to understand the specific use cases and the NN and DL models developed for these areas. The main objective of the course is-
- An introductory segment reviews topic which includes inheritance, the ANSI C++ Standard Library, templates. Input and Output streams, and practical issues of C++ programming, such as reliability, testing, efficiency and interfacing to C.
- Participants will be able to understand the background of Neural networks and Deep learning
- Participants will know how to use a neural network and understand the data needs of deep learning
- Participants will have a working knowledge of MLP
5 Days
Pre-Requisites
Basic Computer skills and programming knowledge
Course Outline
- What is Machine Learning?
- What is a Neural Network?
- What is Deep Learning?
- What is Artificial Intelligence?
- What can be learned from Deep Learning?
- Deep DL vs AI
- Requirements
- Tools needed
- Overview of the steps
- Demonstration building a Neural Network
- Why TensorFlow?
- Computational graph
- Regression example
- Tensor board
- Modularity
- Hands-On- Learning about TensorFlow
- Basics of Neural
- Networks
- Standardization
- Regularization
- Working example
- Application areas
- Hands-On- Using an MLP
- Understanding CNNs
- Comparison to MLP
- Using Multiple Filters
- Working example
- Application areas
- Hands-On: Using a CNN
- Understanding RNN
- Comparison to MLP
- LSTM
- Working example
- Application areas
- Hands-On: Using an LSTM model
- Understanding recursion
- Understanding recursive Neural Networks
- Working example
- Application areas
- Hands-On: Using a recursive Neural Network