AI & Deep Learning workshop

About Two Days AI & Deep Learning workshop

We will conduct two days  AI & Deep Learning workshop is a fast-paced program designed to give the students hands-on experience in AI. This workshop is primarily targeted at students who wish to discover the new technology by hands on training session. In this workshop, The objective of the workshop is to introduce fundamentals of artificial intelligence, convolutional neural networks (CNN), perceptron in CNN, TensorFlow, TensorFlow code, transfer learning, graph visualization, recurrent neural networks (RNN), Deep Learning libraries, GPU in Deep Learning, Keras and TFLearn APIs, backpropagation, and hyperparameters via hands-on projects.

• Pattern recognition, Image classification techniques.
• Understand the intuition behind Artificial Neural Networks
• Apply Artificial Neural Networks in practice
• Understand the intuition behind Convolutional Neural Networks
• Apply Convolutional Neural Networks in practice

Two Days AI Course Outlines

Introduction  Artificial Intelligence

• AI Applications, Types of Learning, Supervised,
• Unsupervised and Reinforcement learning.
• Artificial Neural Networks (ANNs) Concept,
• Feed Forward Neural Networks and Back Propagation

Getting Started with python

• Environment Setup
• Setting up Anaconda, Spyder/VS Code
• Installing Libraries
• Working with Python Framework for Data Science
• Python for Data Analysis-NumPy

Artificial Neural Networks

• The Neuron Diagram Neuron Models & Neural Network
• Functioning of Neurons Activation functions Gradient Descent,
• Stochastic Descent, ramp function, sigmoid function, Gaussian function
• single-layer feed-forward, Multi-layer feed-forward,

CNNs (Convolutional Neural Networks)

• What is a convolutional neural network?
• understanding the architecture and use-cases of CNN,
• how to visualize using CNN,
• how to fine-tune a convolutional neural network,
• understanding recurrent neural networks
• deploying convolutional neural networks in TensorFlow.

RNNs (Recurrent Neural Networks)

• Introduction to the RNN model
• Use cases of RNN,
• training RNNs with back propagation,
• long short-term memory (LSTM),
• Recursive Neural Tensor Network theory,
• the basic RNN cell, unfolded RNN, RNN training, dynamic RNN, and time-series predictions.

Artificial Intelligence Projects

• For recognizing handwritten digits (MNIST dataset)
• Image Recognition with TensorFlow
• Ecommerce Product Recommendation
• Modern Face Recognition with Deep Learning
• Case Study: Cancer Detection, Character Recognition, Iris Clustering
• Case Study: Intelligent Washing Machine Design
• Develop a predictive analytics model for a complex dataset