Artificial Intelligence,  Machine Learning & Deep Learning with Python

Course Overview

This course has been composed by two expert Data Scientists with the goal that we can share our insight and enable you to learn complex hypothesis, calculations and coding libraries just.

Significant learning addresses its genuine forefront. In this course, you’ll develop a sensible understanding of the motivation for significant learning, and layout vigilant structures that pick up from complex and moreover generous scale datasets.

Manmade brainpower will characterize the up and coming age of programming arrangements. This software engineering course gives a review of AI, and clarifies how it can be utilized to assemble brilliant applications that assistance associations be more proficient and advance individuals’ lives.

Course Objective

Manmade brainpower, Machine Learning and Deep learning strategies are winding up exponentially more vital because of their exhibited accomplishment at handling complex learning issues. In the meantime, expanding access to elite figuring assets and cutting edge open-source libraries are making it more attainable for ventures, little firms, and people to utilize these strategies.

Course Outcome

After the completion of this Training, you ought to have the capacity to:

  • Define Deep Learning
  • Express the inspiration driving Deep Learning
  • Apply Analytical arithmetic on the information
  • Choose between various Deep systems
  • Explain Neural systems
  • Train Neural systems
  • Discuss Backpropagation

Prerequisites

This is a moderate to cutting edge level course. Before taking this course, and notwithstanding the essentials and necessities delineated for the Machine Learning Engineer Nanodegree program, you ought to have the accompanying knowledge and aptitudes:

  • Intermediate Programming knowledge (ideally in Python)
  • Basic machine learning information (particularly directed learning)

FAQ’S

Do I require a Windows PC to finish the course?

  • No. You can finish the labs utilizing a PC running Windows, Mac OS X, or Linux.

Imagine a scenario in which I miss a class.
You can pick both of the two alternatives:

  •  View the recorded session of the class accessible in your LMS.
  • You can go to the missed session, in some other live group.

Course Curriculum

  • Basics of AI & Introduction

    • Artificial Intelligence
      0m
    • Environmental Constraints
      0m
    • Various Agent Types
      0m
    • PEAS Analysis of Problem
      0m
    • CSP – Introduction
      0m
    • Process flow for an AI agent
      0m
    • Machine Learning Introduction
      0m
    • Supervised & Unsupervised Learning
      0m
    • Regression & Classification Problems
      0m
    • Advantages & Disadvantages of Naïve Bayes Models
      0m
  • Linear Regression

    • Regression Problem Analysis
      0m
    • Mathematical modelling of Regression Model
      0m
    • Gradient Descent Algorithm
      0m
    • Programming Process Flow
      0m
    • Use cases
      0m
    • Programming Using python
      0m
    • Building simple Univariate Linear Regression Model
      0m
    • Multivariate Regression Model
      0m
    • Boston Housing Prizes Prediction
      0m
    • Project: Cancer Detection Predictive Analysis
      0m
    • Best Fit Line and Linear Regression
      0m
  • Decision Trees

    • Forming a Decision Tree
      0m
    • Components of Decision Tree
      0m
    • Mathematics of Decision Tree
      0m
    • Decision Tree Evaluation
      0m
    • Practical Examples & Case Study
      0m
    • Random Forest
      0m
  • Naïve Bayes

    • Bayesian Theorem
      0m
    • Probabilities – The Prior and Posterior Probabilities
      0m
    • Conditional and Joint Probabilities Notion
      0m
    • Traditional Approach – Extract Important Features
      0m
    • Naive Approach – Independence of Features Assumption
      0m
    • Data Processing – Discretization of Features
      0m
  • Logistic Regression

    • Problem Analysis
      0m
    • Cost Function Formation
      0m
    • Mathematical Modelling
      0m
    • Use Cases
      0m
    • Digit Recognition using Logistic Regression
      0m
  • Artificial Neural Networks

    • Neurons, ANN & Working
      0m
    • Single Layer Perceptron Model
      0m
    • Multilayer Neural Network
      0m
    • Feed Forward Neural Network
      0m
    • Cost Function Formation
      0m
    • Applying Gradient Descent Algorithm
      0m
    • Backpropagation Algorithm & Mathematical Modelling
      0m
    • Programming Flow for backpropagation algorithm
      0m
    • Use Cases of ANN
      0m
    • Programming SLNN using Python
      0m
    • Programming MLNN using Python
      0m
    • Digit Recognition using MLNN
      0m
    • XOR Logic using MLNN & Backpropagation
      0m
    • Diabetes Data Predictive Analysis using ANN
      0m
    • Project – Banking Problem Analysis – When the customer will leave?
      0m
    • Project – Medical Problem Analysis
      0m
  • Support Vector Machine

    • Concept and Working Principle
      0m
    • Mathematical Modelling
      0m
    • Optimization Function Formation
      0m
    • The Kernel Method and Nonlinear Hyperplanes
      0m
    • Use Cases
      0m
    • Programming SVM using Python
      0m
    • Character recognition using SVM
      0m
    • Regression problem using SVM
      0m
    • Wisconsin Cancer Detection using SVM
      0m
  • Image Processing with Opencv

    • Image Acquisition and manipulation using opencv
      0m
    • Video Processing
      0m
    • Edge Detection
      0m
    • Corner Detection
      0m
    • Face Detection
      0m
    • Image Scaling for ANN
      0m
    • Training ANN with Images
      0m
    • Character Recognition
      0m
  • Clustering

    • Hierarchical Clustering
      0m
    • K Means Clustering
      0m
    • Use Cases for K Means Clustering
      0m
    • Programming for K Means using Python
      0m
    • Image Color Quantization using K Means Clustering Technique
      0m
  • Principle Component Analysis

    • Dimensionality Reduction, Data Compression
      0m
    • Concept and Mathematical modelling
      0m
    • Use Cases
      0m
    • Programming using Python
      0m
  • Deep Learning Networks Introduction to TensorFlow

    • The Programming Model
      0m
    • Data Model
      0m
    • Tensor Board
      0m
    • Introducing Feed Forward Neural Nets
      0m
    • Softmax Classifier
      0m
    • ReLU Classifier
      0m
    • Dropout Optimization
      0m
    • Deep Learning Applications
      0m
  • Convolutional Neural Networks

    • CNN Architecture
      0m
    • Pooling
      0m
    • Variants of the Basic Convolution Function
      0m
    • Efficient Convolution Algorithms
      0m
    • The Neuroscientific Basis for Convolutional Networks
      0m
  • Recurrent and Recursive Nets

    • Basic concepts of RNN
      0m
    • Unfolding Recurrent Neural Networks
      0m
    • The Vanishing Gradient Problem
      0m
    • LSTM Networks
      0m
    • Recursive Neural Networks
      0m
    • Deep Belief Networks
      0m
    • Case study
      0m
    • RBM – Concept, Mathematics, Programming & Example
      0m
    • Autoencoders
      0m
    • Concept and methods
      0m
    • CIFAR dataset Analysis
      0m
    • MNIST Data set Analysis
      0m
  • Natural Language Processing

    • Natural Language Processing & Generation
      0m
    • Semantic Analysis
      0m
    • Syntactic Analysis
      0m
    • Language Translation
      0m
    • Using NLTK
      0m
    • Using Textblob
      0m
    • Sentiment Analysis
      0m
    • Project: Streaming live tweets and Sentiment Analysis
      0m

Instructors

Admin bar avatar

Santosh has around 18 years of IT experience, out of which and more than 14 years’ experience in Application Design, managing and Development focuses in SAP, Data Science and E-commerce. He has around 11 years of Service/Project/Program Management across various continents (Europe, Americas and Asia). Worked on ASAP and Agile implementation Methodology.
He is having real-time experience on AI & Machine Learning, He is having 10+ Year experience in IBM Industry

A Technical expert and a passionate trainer has expertise in the field of Internet of Things and Machine Learning, Technical Training and Project Management, he has a proven work record of delivering Technical Training in various technologies and domains at the premier organizations.. He has delivered 50+ corporate Training to clients from India and abroad.

INTERNET OF THINGS
• Corporate Clients – UST Global, mphasis, Accenture, UST Global, CompuCom etc,
• Guest Speaker at 3+ International Conferences and Summits on IoT, Smart City Development and Technological Advancements.
• Designed Course material for online courses on IoT, AI & Machine Learning
• Worked 3+ Industrial IoT Projects

ARTIFICIAL INTELLIGENCE & MACHINE LEARNING
• Corporate Clients – Kronos, HARMAN, mphasis, Accenture, Ericsson, UTC etc,
• Delivered Online training on Machine Learning, Artificial Intelligence and Internet of things to clients from Saudi Countries, South Africa, Bangladesh & US
• Delivered 100+ Lectures across pan India including IIT Roorkee, IIT Kanpur, IIT Jodhpur, IIT Chennai, IIT Bhubaneswar, NIT Sikkim, NIT Surathkal etc.
• Machine learning techniques and algorithms: Good practical experience on complex data for recommendation process, churn and classification, using Random forest, SVM, K-NN, Neural Network, and other decision tree techniques (CHAID, CART)

Reviews

0
0 rating
5 stars
0
4 stars
0
3 stars
0
2 stars
0
1 star
0
Meander Software Private Limited
locationDelhi
experience3-5 years
Talent Corner Hr Services Private Limited
locationPune
experience2-5 years
Techinflo Solutions Private Limited
locationBengaluru / Bangalore
experience1-3 years
SummitWorks Technologies Private Limited
locationBengaluru / Bangalore
experience7-17 years
ALLEGIS SERVICES (INDIA) PRIVATE LIMITED (RPO)
locationBengaluru / Bangalore
experience4-9 years
Wipro Limited
locationBengaluru / Bangalore
experience1-6 years