Neural Network

Neural networks, a beautiful biologically-inspired programming paradigm which enables a computer to learn from observational data. In other words, the neural network uses the examples to automatically infer rules for recognizing handwritten digits. With this workshop participants will have opportunity to learn about artificial neural networks and how they’re being used for machine learning, as applied to speech and object recognition, image segmentation, modeling language and human motion, etc. The session will be emphasized over basic algorithms and the practical tricks needed to get them to work well.

Prerequisites:-

Can access computer system and make use of internet to perform search over Google.

Need to Prepare?

Knowledge of Matrix will be appreciated.Prior programming experience is not required.

Tools Expected:-

Windows OS based PC, Smart phone with Internet, Notebook and Pen

Tools Provided (for the session):-

MATLAB, OCTAVE GUI, OCTAVE CLI, and Reference Material

Concepts:-

Supervised & Unsupervised learning, Linear and Logistics Regression, MATLAB, Neuron & Brain

Summary:-

This workshop is all about develop a model inspired by how the brain works. It is widely used today in many applications: when your phone interprets and understand your voice commands, it is likely that a neural network is helping to understand your speech; when you cash a check, the machines that automatically read the digits also use neural networks.

Project:-

  • Programming: Linear Regression
  • Programming: Logistic Regression
  • Programming: Multi-class Classification and Neural Network
  • Programming: Neural Network Learning

 

Commitment:-

2 Days (7 hours each including 1-hour lunch break)

Agenda:-

Day 1

Session 1-  (03:30 hrs)

Introduction
  • Welcome to Machine Learning!
  • Machine Learning Honor Code
  • What is Machine Learning?
  • Supervised Learning
  • Unsupervised Learning
 Linear Regression with One Variable

    [ Linear regression predicts a real-valued output based on an input value.]

  • Model Representation
  • Cost Function
  • Cost Function – Intuition I
  • Cost Function – Intuition II
  • Gradient Descent
  • Gradient Descent Intuition
  • Gradient Descent For Linear Regression
 
Linear Regression with Multiple Variables
  • Matrices and Vectors
  • Installing MATLAB
  • Installing Octave on Windows
  • Multiple Features
  • Gradient Descent for Multiple Variables
  • Gradient Descent in Practice I – Feature Scaling
  • Gradient Descent in Practice II – Learning Rate
  • Features and Polynomial Regression
  • Normal Equation
  • Normal Equation Noninvertibility
 
Session 2- (02:30 hrs)
Octave / Matlab
  • Basic Operation
  • Moving Data Around
  • Computing on Data
  • Plotting Data
  • Control Statements: for, while, if statement
  • Vectorization
  • Programming: Linear Regression
 
Logistic Regression

         [Logistic regression is a method for classifying data into discrete outcomes.]

  • Classification
  • Hypothesis Representation
  • Decision Boundary
  • Cost Function
  • Simplified Cost Function and Gradient Descent
  • Advanced Optimization
  • Multiclass Classification: One-vs-all
Session Recap
 
Day 2
Session 1- (03:30 hrs)
Regularization

         [Prevent models from overfitting the training data.]

  • The Problem of Overfitting
  • Cost Function
  • Regularized Linear Regression
  • Regularized Logistic Regression
  • Programming: Logistic Regression
Neural Networks: Representation

[Neural networks is a model inspired by how the brain works. ]

  • Non-linear Hypotheses
  • Neurons and the Brain
  • Model Representation I
  • Model Representation II
  • Examples and Intuitions I
  • Examples and Intuitions II
  • Multiclass Classification
  • Programming: Multi-class Classification and Neural Network
Session 2- (02:30 hrs)
Neural Network Learning

      [understand the backpropagation algorithm that is used to help learn parameters for a neural network.]

  • Cost Function
  • Backpropagation Algorithm
  • Backpropagation Intuition
  • Implementation Note: Unrolling Parameters
  • Gradient Checking
  • Random Initialization
  • Putting It Together
  • Autonomous Driving
  • Programming: Neural Network Learning
Session Recap
 
Zonal Round of SkillThon
  • Competition
  • Certificate distribution and acknowledgement
 

Charges:

INR 1200 (GST exclusive) Per Participation