GUVI | AI Combo Pack

Artificial Intelligence Combo Pack

Upskill yourself with the most in-demand career choice of AI with our Artificial Intelligence Combo Pack.

Whether you’re just learning to code or already have experience, you’ll find this course helpful you develop your skills and advance your projects.

In this training you will learn various aspects of AI like Deep Learning with Pytorch, Machine Learning, Artificial Neural Networks, Expert systems, Object Detection and Vernacular Language Signboard Translation as a Capstone Project.

You will get 12 Deep Learning module certificates and 3 final certificate.This program will prepare you to solve real world problems using cutting edge technologies.

Key Features

Course taught by IIT Madras Professors who are subject matter experts in the field.
100+ hours of self paced videos with Lifetime Access.
15 Modules certifications.
Globally Recognized Certificate from GUVI after successful completion
Dedicated Forum Support from the Instructors
100% Online Learning
Access to community of DL Students and Enthusiasts
Frequent Kaggle contests
7 days Refund Policy

Pre-requisites

Time commitment of 4 hours a week.
Laptop / desktop with internet access.

What you'll get in this pack

Python
Machine Learning
Deep Learning

Who Should Enroll in this course

IT Professionals
IT Consultants
IT Graduates & Freshers
Any Graduate with Programming Knowledge

Fee structure

Student/Faculty

Eligibility Students enrolled in schools/colleges without any prior work experience and faculty members of colleges and universities. Requisites Applicants must provide a valid details indicating their present enrolment in any recognised educational institution. Fee Structure ~~16800~~ 3699 (You Save: 78% )

Professional

Eligibility Working professionals from companies and any other applicant with work-experience looking to upskill. Requisites Nil. Just apply directly. Fee Structure ~~16800~~ 8399 (You Save: 50% )

About instructors

Arun Prakash is the Founder & Chief Technology Officer of GUVI. He is a technologist with more than 17 years of experience. He has worked with bigwigs like Paypal, Symantec & Honeywell in the past.

Janani has a Masters degree from Stanford and worked for 7+ years at Google. She was one of the original engineers on Google Docs and holds 4 patents for its real-time collaborative editing framework. After spending years working in tech in the Bay Area, New York, and Singapore at companies such as Microsoft, Google, and Flipkart, Janani finally decided to combine her love for technology with her passion for teaching. She is now the co-founder of Loonycorn, a content studio focused on providing high-quality content for technical skill development. Loonycorn is working on developing an engine (patent filed) to automate animations for presentations and educational content.

Mitesh M. Khapra is an Assistant Professor in the Department of Computer Science and Engineering at IIT Madras. He researches in the areas of Deep Learning, Multimodal Multilingual Processing, Dialog systems and Question Answering. He holds masters and Ph.D degrees from IIT Bombay. He has worked for over 4.5 years at IBM Research and published over 25 papers. He was a recipient of IBM PhD Fellowship and the Microsoft Rising Star Award. He is also a recipient of the Google Faculty Research Award, 2018.

Pratyush is an Assistant Professor at the Department of Computer Science and Engineering at IIT Madras since April 2018. He received his Bachelors and Masters of Technology in Electrical Engineering from IIT Bombay in 2009. He then completed his PhD in Computer Engineering from ETH Zurich in 2014. He then spent over 2.5 years at IBM Research, Bangalore and a few months consulting for machine learning and startups. His current research focus is on hardware-software co-design of deep learning systems. He has authored over 35 research papers and has applied for over 20 patents.

Syllabus

Machine Learning

17 Lesson

3 hrs

About Machine Learning Course
Installation of Anaconda
What is Machine Learning
Types of Machine Learning, Supervised Learning and Regression
Types of ML,Logistic Regression and Unsupervised Learning
SVM -What is SVM and How do they work
SVM-Loading and Examining our dataset
SVM-Building and Tweaking our SVM Classification mode
What is Decision Tree?
Building the Decision Tree : Decision Tree Learning
Building a Decision Tree - Information Gain a Gini Impurity
Decision Tree Lab:Building our First Decision Tree
Decision Tree Lab:Viewing and Tweaking our Decision Tree
What is Overfitting
Random Forest Lab
Teamwork
Avoiding Overfitted Models

DL#101 - Getting Started

37 Lesson

10 hrs

Python Basics: Google Colaboratory
Python Basics: Basic Data Types
Python Basics: Lists
Python Basics: Tuples, Sets, Dictionaries
Python Basics: Packages
Python Basics: File Handling
Python Basics: Classes
Python Basics: Numpy
Python Basics: Plotting
Expert Systems & 6 Jars: Expert Systems
Expert Systems & 6 Jars: Say Hi To ML
Expert Systems & 6 Jars: Introduction
Expert Systems & 6 Jars: Data
Expert Systems & 6 Jars: Tasks
Expert Systems & 6 Jars: Models
Expert Systems & 6 Jars: Loss Function
Expert Systems & 6 Jars: Learning Algorithm
Expert Systems & 6 Jars: Evaluation
Expert Systems & 6 Jars: Six Jars Summary (Part 1)
Expert Systems & 6 Jars: Six Jars Summary (Part 2)
Vectors & Matrices: Introduction to Vectors
Vectors & Matrices: Dot product of vectors
Vectors & Matrices: Unit Vectors
Vectors & Matrices: Projection of one vector onto another
Vectors & Matrices: Angle between two vectors
Vectors & Matrices: Why do we care about vectors?
Vectors & Matrices: Introduction to Matrices
Vectors & Matrices: Multiplying a vector by a matrix
Vectors & Matrices: Multiplying a matrix by another matrix
Vectors & Matrices: An alternate way of multiplying two matrices
Vectors & Matrices: Why do we care about matrices?
Python Basics + Linear Algebra: Google Drive and Colab Integration
Python Basics + Linear Algebra: Pandas
Python Basics + Linear Algebra: Python Debugger
Python Basics + Linear Algebra: Plotting Vectors
Python Basics + Linear Algebra: Vector Addition and Subtraction
Python Basics + Linear Algebra: Vector Dot Product

DL#102 - Primitive Neurons

38 Lesson

10 hrs

MP Neuron: Introduction
MP Neuron: Model
MP Neuron: Data & Task
MP Neuron: Loss
MP Neuron: Learning
MP Neuron: Evaluation
MP Neuron: Geometry Basics
MP Neuron: Geometric Interpretation
MP Neuron: Summary
Perceptron: Introduction
Perceptron: Data & Task
Perceptron: Model
Perceptron: Geometric Interpretation
Perceptron: Loss Function
Perceptron: Learning - General Recipe
Perceptron: Learning Algorithm
Perceptron: Learning - Why it Works?
Perceptron: Learning - Will it Always Work?
Perceptron: Evaluation
Perceptron: Summary
MP Neurons & Perceptron using Python: Toy Example (Perceptron)
MP Neurons & Perceptron using Python: Loading Data
MP Neurons & Perceptron using Python: Train-Test Split
MP Neurons & Perceptron using Python: Binarization
MP Neurons & Perceptron using Python: Inference And Search
MP Neurons & Perceptron using Python: Inference
MP Neurons & Perceptron using Python: Class
MP Neurons & Perceptron using Python: Perceptron Class
MP Neurons & Perceptron using Python: Epochs
MP Neurons & Perceptron using Python: Checkpointing
MP Neurons & Perceptron using Python: Learning Rate
MP Neurons & Perceptron using Python: Weight Animation
MP Neurons & Perceptron using Python: Exercises
Contest - Mobile Phone Like/Dislike predictor: Introduction to Contests.
Contest - Mobile Phone Like/Dislike predictor: Creating a Kaggle account
Contest - Mobile Phone Like/Dislike predictor: Data preprocessing
Contest - Mobile Phone Like/Dislike predictor: Submitting Entries
Contest - Mobile Phone Like/Dislike predictor: Clarifications

DL#103 - Sigmoid Neuron

57 Lesson

10 hrs

6 Jars of Sigmoid Neuron (I): Recap from last lecture
6 Jars of Sigmoid Neuron (I):Revisiting limitations of perceptron model
6 Jars of Sigmoid Neuron (I): Sigmoid Model Part 1
6 Jars of Sigmoid Neuron (I): Sigmoid Model Part 2
6 Jars of Sigmoid Neuron (I): Sigmoid Model Part 3
6 Jars of Sigmoid Neuron (I): Sigmoid Model Part 4
6 Jars of Sigmoid Neuron (I): Sigmoid: Data and Tasks
6 Jars of Sigmoid Neuron (I): Sigmoid: Loss Function
6 Jars of Sigmoid Neuron (I): Learning: Intro to Learning Algorithm
6 Jars of Sigmoid Neuron (I): Learning: Learning by guessing
6 Jars of Sigmoid Neuron (I): Learning - Error Surfaces for learning
6 Jars of Sigmoid Neuron (I): Learning - Mathematical setup for the learning algorithm
6 Jars of Sigmoid Neuron (I): Learning - The math-free version of learning algorithm
6 Jars of Sigmoid Neuron (II): Learning - Introducing Taylor Series
6 Jars of Sigmoid Neuron (II): Learning - More intuitions about Taylor series
6 Jars of Sigmoid Neuron (II): Learning - Deriving the Gradient Descent Update rule
6 Jars of Sigmoid Neuron (II): Learning - The complete learning algorithm
6 Jars of Sigmoid Neuron (II): Learning - Computing Partial Derivatives
6 Jars of Sigmoid Neuron (II): Learning - Writing the code
6 Jars of Sigmoid Neuron (II): Sigmoid - Dealing with more than 2 parameters
6 Jars of Sigmoid Neuron (II): Sigmoid - Evaluation
6 Jars of Sigmoid Neuron (II): Summary and take-aways
Sigmoid Neurons Using Python (I): Plotting Sigmoid 2D
Sigmoid Neurons Using Python (I): Plotting Sigmoid 3D
Sigmoid Neurons Using Python (I): Plotting Loss
Sigmoid Neurons Using Python (I): Contour Plot
Sigmoid Neurons Using Python (I): Class
Sigmoid Neurons Using Python (I): Toy Data Fit
Sigmoid Neurons Using Python (I): Toy Data Plot - 1/2
Sigmoid Neurons Using Python (I): Toy Data Plot - 2/2
Sigmoid Neurons Using Python (II): Loading Data
Sigmoid Neurons Using Python (II): Standardisation
Sigmoid Neurons Using Python (II): Test/Train Split (1/2)
Sigmoid Neurons Using Python (II): Test/Train Split (2/2)
Sigmoid Neurons Using Python (II): Fitting Data
Sigmoid Neurons Using Python (II): Loss Plot
Sigmoid Neurons Using Python (II): Progress Bar
Sigmoid Neurons Using Python (II): Exercises
Probability Theory Introduction
Probability Theory: Random Variable - Intuition
Probability Theory: Random Variable - Formal Definition
Probability Theory: Random Variable - Continuous and Discrete
Probability Theory: Probability Distribution
Probability Theory: True and Predicted Distribution
Probability Theory: Certain Events
Probability Theory: Why Do we Care About Distributions
Information Theory and Cross Entropy: Expectation
Information Theory and Cross Entropy: Information Content
Information Theory and Cross Entropy: Entropy
Information Theory and Cross Entropy: Relation To Number Of Bits
Information Theory and Cross Entropy: KL-Divergence and Cross Entropy
Information Theory and Cross Entropy: Sigmoid Neuron and Cross Entropy
Information Theory and Cross Entropy: Using Cross Entropy With Sigmoid Neuron
Information Theory and Cross Entropy: Learning Algorithm for Cross Entropy loss function
Information Theory and Cross Entropy: Computing partial derivatives with cross entropy loss
Information Theory and Cross Entropy: Code for Cross Entropy Loss function
Contest - Text, Non-Text Classification: Overview

DL#104 - Feedforward Neural Networks

25 Lesson

10 hrs

Representation Power of function: Why do we need complex functions
Representation Power of function: Complex functions in real world examples
Representation Power of function: A simple recipe for building complex functions
Representation Power of function: Illustrative Proof of Universal Approximation Theorem
Representation Power of function: Summary
Deep Neural Networks: Setting the context
Deep Neural Networks: Data and Tasks
Deep Neural Networks: Model: A simple deep neural network
Deep Neural Networks: Model: A generic deep neural network
Deep Neural Networks: Model: Understanding the computations in a deep neural network
Deep Neural Networks: Model: The output layer of a deep neural network
Deep Neural Networks: Model: Output layer of a multi-class classification problem
Deep Neural Networks: Model: How do you choose the right network configuration
Deep Neural Networks: Loss function for binary classification
Deep Neural Networks: Loss function for multi-class classification
Deep Neural Networks: Learning Algorithm (non-mathy version)
Deep Neural Networks: Evaluation
Deep Neural Networks: Summary
DNNs using Python: Outline
DNNs using Python: Generating Data
DNNs using Python: Classification with Sigmoid Neuron
DNNs using Python: Classification with FF Network
DNNs using Python: Generic Class of FF Neuron
DNNs using Python: Multi Class Classification with FF Network
DNNs using Python: Exercise

DL#105 - Training Feedforward Neural Networks

41 Lesson

10 hrs

Backpropagation - the light math version: Setting the context
Backpropagation - the light math version: Revisiting Basic Calculus
Backpropagation - the light math version: Why do we care about the chain rule of derivatives
Backpropagation - the light math version: Applying chain rule across multiple paths
Backpropagation - the light math version: Applying Chain rule in a neural network
Backpropagation - the light math version: Computing Partial Derivatives w.r.t. a weight - Part 1
Backpropagation - the light math version: Computing Partial Derivatives w.r.t. a weight - Part 2
Backpropagation - the light math version: Computing Partial Derivatives w.r.t. a weight - Part 3
Backpropagation - the light math version: Computing Partial Derivatives w.r.t. a weight when there are multiple paths
Backpropagation - the light math version: Takeaways and what next ?
Backpropagating using Python: Outline
Backpropagating using Python: Single Weight Update
Backpropagating using Python: Single Weight Training
Backpropagating using Python: Multiple Weight Update
Backpropagating using Python: Visualising Outputs
Backpropagating using Python: Visualising Weights
Backpropagating using Python: Backpropagation for Multiple Class Classification
Backpropagating using Python: Shortened Backpropagation Code
Backpropagating using Python: Exercises
Backpropagation - the full version: Errata from last theory slot
Backpropagation - the full version: Setting the Context
Backpropagation - the full version: Intuition behind backpropagation
Backpropagation - the full version: Understanding the dimensions of gradients
Backpropagation - the full version: Computing Derivatives w.r.t. Output Layer - Part 1
Backpropagation - the full version: Computing Derivatives w.r.t. Output Layer - Part 2
Backpropagation - the full version: Computing Derivatives w.r.t. Output Layer - Part 3
Backpropagation - the full version: Quick recap of the story so far
Backpropagation - the full version: Computing Derivatives w.r.t. Hidden Layers - Part 1
Backpropagation - the full version: Computing Derivatives w.r.t. Hidden Layers - Part 2
Backpropagation - the full version: Computing Derivatives w.r.t. Hidden Layers - Part 3
Backpropagation - the full version: Computing derivatives w.r.t. one weight in any layer
Backpropagation - the full version: Computing derivatives w.r.t. all weights in any layer
Backpropagation - the full version: A running example of backpropagation
Backpropagation - the full version: Summary
Backpropagating - the full version using Python: Outline
Backpropagating - the full version using Python: Benefits of Vectorisation
Backpropagating - the full version using Python: Scalar Class - Recap
Backpropagating - the full version using Python: Vectorising weights
Backpropagating - the full version using Python: Vectorising inputs and weights
Backpropagating - the full version using Python: Evaluation of Classes
Backpropagating - the full version using Python: Exercises

DL#106 - Optimization Algorithms

70 Lesson

10 hrs

Variants of Gradient Desscent: A quick history of DL to set the context
Variants of Gradient Desscent: Highlighting a limitation of Gradient Descent
Variants of Gradient Descent: A deeper look into the limitation of gradient descent
Variants of Gradient Descent: Introducing contour maps
Variants of Gradient Descent: Exercise: Guess the 3D surface
Variants of Gradient Descent: Visualizing gradient descent on a 2D contour map
Variants of Gradient Descent: Intuition for momentum based gradient descent
Variants of Gradient Descent: Dissecting the update rule for momentum based gradient descent
Variants of Gradient Descent: Running and visualizing momentum based gradient descent
Variants of Gradient Descent: A disadvantage of momentum based gradient descent
Variants of Gradient Descent: Intuition behind nesterov accelerated gradient descent
Variants of Gradient Descent: Running and visualizing nesterov accelerated gradient descent
Variants of Gradient Descent: Summary and what next
Variants of Gradient Descent: The idea of stochastic and mini-batch gradient descent
Variants of Gradient Descent: Running stochastic gradient descent
Variants of Gradient Descent: Running mini-batch gradient descent
Variants of Gradient Descent: Epochs and Steps
Variants of Gradient Descent: Why do we need an adaptive learning rate ?
Variants of Gradient Descent: Introducing Adagrad
Variants of Gradient Descent: Running and Visualizing Adagrad
Variants of Gradient Descent: A limitation of Adagrad
Variants of Gradient Descent: Running and visualizing RMSProp
Variants of Gradient Descent: Running and visualizing Adam
Variants of Gradient Descent: Summary
Implementing Optimization Algorithms Using Python: Outline
Implementing Optimization Algorithms Using Python: Modified Sigmoid Neuron Class
Implementing Optimization Algorithms Using Python: Setup for Plotting
Implementing Optimization Algorithms Using Python: Gradient Descent Algorithm
Implementing Optimization Algorithms Using Python: GD Algorithm - Contour Plot
Implementing Optimization Algorithms Using Python: Momentum
Implementing Optimization Algorithms Using Python: Nesterov Accelerated GD
Implementing Optimization Algorithms Using Python: Mini-Batch GD
Implementing Optimization Algorithms Using Python: AdaGrad
Implementing Optimization Algorithms Using Python: RMSProp
Implementing Optimization Algorithms Using Python: Adam
Implementing Optimization Algorithms Using Python: Vectorised Class Recap
Implementing Optimization Algorithms Using Python: Vectorised GD Algorithms
Implementing Optimization Algorithms Using Python: Performance of Different Algorithms
Implementing Optimization Algorithms Using Python: Good solutions and Exercise
Activation Functions & Initialization Methods: Setting the context
Activation Functions & Initialization Methods: Saturation in logistic neuron
Activation Functions & Initialization Methods: Zero centered functions
Activation Functions & Initialization Methods: Introducing Tanh and ReLU activation functions
Activation Functions & Initialization Methods: Tanh and ReLU Activation Functions
Activation Functions & Initialization Methods: Symmetry Breaking Problem
Activation Functions & Initialization Methods: Xavier and He initialization
Activation Functions & Initialization Methods: Summary and what next
Hands-on - activation functions & initialization methods: Introduction and Activation Functions
Hands-on - activation functions & initialization methods: Activation Functions
Hands-on - activation functions & initialization methods: Plotting Setup
Hands-on - activation functions & initialization methods: Sigmoid
Hands-on - activation functions & initialization methods: Tanh
Hands-on - activation functions & initialization methods: ReLu
Hands-on - activation functions & initialization methods: Leaky ReLU
Hands-on - activation functions & initialization methods: Exercises
Regularization: Simple v/s complex models
Regularization: Analysing the behavior of simple and complex models
Regularization: Bias and Variance
Regularization: Test error due to high bias and high variance
Regularization: Overfitting in deep neural networks
Regularization: A detour into hyperparameter tuning
Regularization: L2 regularization
Regularization: Dataset Augmentation and Early Stopping
Regularization: Summary
Hands-on - Regularization: Outline and Libraries
Hands-on - Regularization: L2 Regularisation in Code
Hands-on - Regularization: Bias on Increasing Model Complexity
Hands-on - Regularization: L2 Regularisation in Action
Hands-on - Regularization: Adding Noise to Input Features
Hands-on - Regularization: Early Stopping and Exercises

DL#107 - Introduction to Pytorch

15 Lesson

10 hrs

Basics of Pytorch: Outline
Basics of Pytorch: PyTorch Tensors
Basics of Pytorch: Simple Tensor Operations
Basics of Pytorch: NumPy vs PyTorch
Basics of Pytorch: GPU PyTorch
Basics of Pytorch: Automatic Differentiation
Basics of Pytorch: Loss Function with AutoDiff
Basics of Pytorch: Learning Loop GPU
FNNs using Pytorch: Outline
FNNs using Pytorch: Forward Pass With Tensors
FNNs using Pytorch: Functions for Loss, Accuracy, Backpropagation
FNNs using Pytorch: PyTorch Modules - NN and Optim
FNNs using Pytorch: NN Sequential and Code Structure
FNNs using Pytorch: GPU Execution
FNNs using Pytorch: Exercises and Recap

DL#108 - Convolutional Neural Networks

24 Lesson

10 hrs

The convolution operation: Setting the Context
The convolution operation: The 1D convolution operation
The convolution operation: The 2D Convolution Operation
The convolution operation: Examples of 2D convolution
The convolution operation: 2D convolution with a 3D filter
The convolution operation: Terminilogy
The convolution operation: Padding and Stride
From convolution operation to neural networks: How is the convolution operation related to Neural Networks - Part 1
From convolution operation to neural networks: How is the convolution operation related to Neural Networks - Part 2
From convolution operation to neural networks: How is the convolution operation related to Neural Networks - Part 3
From convolution operation to neural networks: Understanding the input/output dimensions
From convolution operation to neural networks: Sparse Connectivity and Weight Sharing
From convolution operation to neural networks: Max Pooling and Non-Linearities
From convolution operation to neural networks: Our First Convolutional Neural Network (CNN)
From convolution operation to neural networks: Training CNNs
From convolution operation to neural networks: Summary and what next
CNNs in Pytorch: Outline
CNNs in Pytorch: Loading Data Sets
CNNs in Pytorch: Visualising Weights
CNNs in Pytorch: Single Convolutional Layer
CNNs in Pytorch: Deep CNNs
CNNs in Pytorch: LeNet
CNNs in Pytorch: Training Le Net
CNNs in Pytorch: Visualising Intermediate Layers, Exercises

DL#109 - Deep Convolutional Neural Networks

61 Lesson

10 hrs

CNN Architectures - Part 1: Setting the context
CNN Architectures - Part 1: The Imagenet Challenge
CNN Architectures - Part 1: Understanding the first layer of AlexNet
CNN Architectures - Part 1: Understanding all layers of AlexNet
CNN Architectures - Part 1: ZFNet
CNN Architectures - Part 1: VGGNet
CNN Architectures - Part 1: Summary
CNN Architectures - Part 2: Setting the context
CNN Architectures - Part 2: Number of computations in a convolution layer
CNN Architectures - Part 2: 1x1 Convolutions
CNN Architectures - Part 2: The Intuition behind GoogLeNet
CNN Architectures - Part 2: The Inception Module
CNN Architectures - Part 2: The GoogleNet Architecture
CNN Architectures - Part 2: Average Pooling
CNN Architectures - Part 2: Auxiliary Loss for training a deep network
CNN Architectures - Part 2: ResNet
Building CNN Architectures Using Pytorch: Outline
Building CNN Architectures Using Pytorch: Image Transforms
Building CNN Architectures Using Pytorch: VGG
Building CNN Architectures Using Pytorch: Training VGG
Building CNN Architectures Using Pytorch: Pre-trained Models
Building CNN Architectures Using Pytorch: Checkpointing Models
Building CNN Architectures Using Pytorch: ResNet
Building CNN Architectures Using Pytorch: Inception Part 1
Building CNN Architectures Using Pytorch: Inception Part 2
Building CNN Architectures Using Pytorch: Exercises
Visualising CNNs: Receptive field of a neuron
Visualising CNNs: Identifying images which cause certain neurons to fire
Visualising CNNs: Visualising filters
Visualising CNNs: Occlusion experiments
Visualising CNNs Using Python: Outline
Visualising CNNs Using Python: Custom Torchvision Dataset
Visualising CNNs Using Python: Visualising inputs
Visualising CNNs Using Python: Occlusion
Visualising CNNs Using Python: Visualising filters
Visualising CNNs Using Python: Visualising filters - code
Batch Normalization and Dropout: Normalizing inputs
Batch Normalization and Dropout: Why should we normalize the inputs
Batch Normalization and Dropout: Batch Normalization
Batch Normalization and Dropout: Learning Mu and Sigma
Batch Normalization and Dropout: Ensemble Methods
Batch Normalization and Dropout: The idea of dropout
Batch Normalization and Dropout: Training without dropout
Batch Normalization and Dropout: How does weight sharing help ?
Batch Normalization and Dropout: Using dropout at test time
Batch Normalization and Dropout: How does dropout act as a regularizer ?
Batch Normalization and Dropout: Summary and what next ?
Batch Normalization and Dropout Using Python: Outline and Dataset
Batch Normalization and Dropout Using Python: Batch Norm Layer
Batch Normalization and Dropout Using Python: Batch Norm Visualisation
Batch Normalization and Dropout Using Python: Batch Norm 2d
Batch Normalization and Dropout Using Python: Dropout layer
Batch Normalization and Dropout Using Python: Dropout Visualisation and Exercises
Hyperparameter Tuning and MLFlow: Outline
Hyperparameter Tuning and MLFlow: Colab on Local Runtime
Hyperparameter Tuning and MLFlow: MLFlow installation and basic usage
Hyperparameter Tuning and MLFlow: Hyperparamater Tuning
Hyperparameter Tuning and MLFlow: Refined Search for Hyperparameters
Hyperparameter Tuning and MLFlow: Logging Image Artifacts
Hyperparameter Tuning and MLFlow: Logging and Loading Models
Hyperparameter Tuning and MLFlow: One Last Visualisation

DL#110 - Sequence Models

61 Lesson

13 hrs

Sequence Learning Problems: Setting the context
Sequence Learning Problems: Introduction to sequence learning problems
Sequence Learning Problems: Some more examples of sequence learning problems
Sequence Learning Problems: Sequence learning problems using video and speech data
Sequence Learning Problems: A wishlist for modelling sequence learning problems
Sequence Learning Problems: Intuition behind RNNs - Part 1
Sequence Learning Problems: Intuition behind RNNs - Part 2
Sequence Learning Problems: Introducing RNNs
Sequence Learning Problems: Summary and what next
Recurrent Neural Networks: Setting the context
Recurrent Neural Networks: Data and Tasks - Sequence Classification - Part 1
Recurrent Neural Networks: Data and Tasks - Sequence Classification - Part 2
Recurrent Neural Networks: A clarification about padding
Recurrent Neural Networks: Data and Tasks - Sequence Labelling
Recurrent Neural Networks: Model
Recurrent Neural Networks: Loss Function
Recurrent Neural Networks: Learning Algorithm
Recurrent Neural Networks: Learning Algorithm - Derivatives w.r.t. V
Recurrent Neural Networks: Learning Algorithm - Derivatives w.r.t. W
Recurrent Neural Networks: Evaluation
Recurrent Neural Networks: Summary and what next
Vanishing and Exploding Gradients: Revisiting the gradient wrt W
Vanishing and Exploding Gradients: Zooming into one element of the chain rule - Part 1
Vanishing and Exploding Gradients: Zooming into one element of the chain rule - Part 2
Vanishing and Exploding Gradients: A small detour to calculus
Vanishing and Exploding Gradients: Looking at the magnitude of the derivative
Vanishing and Exploding Gradients: Exploding and vanishing gradients
Vanishing and Exploding Gradients: Summary and what next
LSTMs and GRUs: Dealing with longer sequences
LSTMs and GRUs: The white board analogy
LSTMs and GRUs: Real world example of longer sequences
LSTMs and GRUs: Going back to RNNs
LSTMs and GRUs: Selective Write - Part 1
LSTMs and GRUs: Selective Write - Part 2
LSTMs and GRUs: Selective Read
LSTMs and GRUs: Selective forget
LSTMs and GRUs: An example computation with LSTMs
LSTMs and GRUs: Gated recurrent units
LSTMs and GRUs: Summary and what next
Sequence Models in PyTorch: OutlineSequence Models in PyTorch: Outline
Sequence Models in PyTorch: Dataset and Task
Sequence Models in PyTorch: RNN Model
Sequence Models in PyTorch: Inference on RNN
Sequence Models in PyTorch: Training RNN
Sequence Models in PyTorch: Training Setup
Sequence Models in PyTorch: LSTM
Sequence Models in PyTorch: GRU and Exercises
Addressing the problem of vansihing and exploding gradients: Quick Recap
Addressing the problem of vansihing and exploding gradients: Intuition: How gates help to solve the problem of vanishing gradients
Addressing the problem of vansihing and exploding gradients: Revisiting vanishing gradients in RNNs
Addressing the problem of vansihing and exploding gradients: Dependency diagram for LSTMs
Addressing the problem of vansihing and exploding gradients: Computing the gradient
Addressing the problem of vansihing and exploding gradients: When do the gradients vanish?
Addressing the problem of vansihing and exploding gradients: Dealing with exploding gradients
Addressing the problem of vansihing and exploding gradients: Summary and what next
Batching for Sequence Models in Pytorch: Overview
Batching for Sequence Models in Pytorch: Recap on Sequence Models
Batching for Sequence Models in Pytorch: Batching for Sequence Models
Batching for Sequence Models in Pytorch: Padding Vector Representations
Batching for Sequence Models in Pytorch: Packing in PyTorch
Batching for Sequence Models in Pytorch: Training with Batched Input

DL#111 - Encoder Decoder Models

25 Lesson

5 hrs

Neural Encoders and Decoders: Setting the context
Neural Encoders and Decoders: Revisiting the task of language modelling
Neural Encoders and Decoders: Using RNNs for language modelling
Neural Encoders and Decoders: Introducing Encoder Decoder Model
Neural Encoders and Decoders: Connecting encoder decoder models to the six jars
Neural Encoders and Decoders: A compact notation for RNNs, LSTMs and GRUs
Neural Encoders and Decoders: Encoder decoder model for image captioning
Neural Encoders and Decoders: Six jars for image captioning
Neural Encoders and Decoders: Encoder decoder for Machine translation
Neural Encoders and Decoders: Encoder decoder model for transliteration
Neural Encoders and Decoders: Summary
Attention Mechanism: Motivation for attention mechanism
Attention Mechanism: Attention mechanism with an oracle
Attention Mechanism: A model for attention
Attention Mechanism: The attention function
Attention Mechanism: Machine translation with attention
Attention Mechanism: Summary and what next
Encoder Decoder Models and Attention Mechanism Using Pytorch: Outline
Encoder Decoder Models and Attention Mechanism Using Pytorch: Data set and Task
Encoder Decoder Models and Attention Mechanism Using Pytorch: Data Ingestion - XML processing
Encoder Decoder Models and Attention Mechanism Using Pytorch: Encoder Decoder Model - 1
Encoder Decoder Models and Attention Mechanism Using Pytorch: Encoder Decoder Model - 2
Encoder Decoder Models and Attention Mechanism Using Pytorch: Adding Attention - 1
Encoder Decoder Models and Attention Mechanism Using Pytorch: Adding Attention - 2
Encoder Decoder Models and Attention Mechanism Using Pytorch: Model Evaluation and Exercises

DL#112 - Introduction to Object Detection

12 Lesson

3 hrs

RCNN: More clarity on regression
RCNN: Setting the context
RCNN: A typical pipeline for object detection
RCNN: Region Proposal
RCNN: Feature Extraction
RCNN: Classification
RCNN: Regression
RCNN: Training
YOLO: Introduction to YOLO
YOLO: The Output of YOLO
YOLO: Training
Object Detection: Summary and what next

DL#113 - Capstone Project

1 Lesson

1 hrs

Capstone Project: Project Details

View all 13 Modules

For futher queries, Write a mail to [email protected]

Sample certificate

Our learners

"This course is the best as it focuses both on the theory and hands on.This course introduced me to Kaggle competitions and I got addicted to it.I feel more confident that I can contribute to real world projects involving deep learning after taking this course."

- Praveen R

"Learned a lot from this course. Before starting this course, I have no knowledge of deep learning but after learning this course I am pretty confident."

- Vudata Rohit

"This course can turn you into a deep learning enthusiast if you have the urge to learn something new (even if you don't know anything about deep learning at all)."

- Kanumuri Sri Naga Sai Ajith

About Deep Learning

Deep learning refers to a set of techniques by which we can achieve varying degrees of artificial intelligence by mimicking the working of a human brain. Deep learning is a subset of Machine Learning techniques that aim to achieve Artificial Intelligence. The distinguishing feature of Deep Learning is its use of various Artificial Neural Networks, that imitate the human brain. Just as in the brain, Artificial Neural Networks or ANNs also consist of neurons and synapses between them. Deep Learning vs Machine Learning: In traditional Machine Learning, the data must be broken down into individual features. These hand-crafted features are fed into the model and we get a prediction as an output. However, hand-crafting features is a time-consuming process that involves a lot of statistical knowledge and expertise in data science. With the advent of Deep Learning and multi-layered Artificial Neural Networks, feature selection can now be handled by the model itself. By feeding it numerical representation of raw data (Images, Video, Audio etc), the multi-layered architecture allows for the model to determine the highest-contributing features and uses them to make successful predictions, without any human crafted features. This drastically shortened project timelines and human intervention in the preliminary stages. A small caveat is that DL models required larger volumes of data to train than traditional ML models. Advantages of Studying Artificial Intelligence: From SIRI to self-driving cars, artificial intelligence (AI) is progressing rapidly. While science fiction often portrays AI as robots with human-like characteristics, AI can encompass anything from Google’s search algorithms to IBM’s Watson to autonomous weapons. Let us discuss some of the advantages studying Artificial Intelligence..

Automates the processes: Artificial Intelligence allows robots to develop repetitive, routine and process optimization tasks automatically and without human intervention.
Enhance creative tasks: AI frees people from routine and repetitive tasks and allows them to spend more time on creative functions.
Helps in Daily Applications: Daily applications such as Apple’s Siri, Window’s Cortana, Google’s OK Google are frequently used in our daily routine whether it is for searching a location, taking a selfie, making a phone call, replying to a mail and many more.
Quick Learning: With around 5-8 hours of study per week and around 6 months of time, learners can progress rapidly from novice to intermediate/adept levels with this AI Combo Pack.

Artificial Intelligence Career Opportunities: Projects @ IT/ITeS Companies: For those looking to transition into AI projects at IT companies, familiarity of programming, application and mathematics behind deep learning will be suitable. DL products @ startups: For those looking to join startups focused on AI products, a working level of proficiency in programming, mathematics and application of AI techniques would be required. Research @ universities, research labs: For those looking to enter the research field, expert understanding of Artificial Intelligence, its underlying concepts and its practical application are required.

Why study through GUVI?

Partner with us

Universities and Colleges If you are an educational institution and would like to adopt our courses for your curriculum, we are very happy to support you. We can bulk enrol your students and provide certification for them to receive appropriate credit at your institution.

Foundations and NGOs If you are a foundation or an NGO and find synergy with our goal of affordable AI education, you can offer support for curriculum design and awards for top- performing students.

Corporates and Startups If you would like to train several of your employees on AI, please write to us to receive customized reports on how they perform. You can also partner with us on the DL garage by defining problem statements and awarding student grants.

Frequently Asked Questions

How is this different from other courses?

The focus of the courses is primarily on combining theoretical knowledge with hands-on experience. Further, the emphasis is to go from limited pre-requisites to solving a challenging problems. Finally, we hope to build a community around PadhAI by continuing to engage with you after the course through the DL garage, subsequent courses, and also through our startup One Fourth Labs which will build solutions on Deep Learning.

Will I get a certificate on completing a course?

Yes, upon successful completion, you will get a certificate from GUVI. This certificate will be accessible to you.

What are the pre-requisites?

We do not expect you to be familiar with AI or related topics. Mathematical understanding equivalent to 12th standard syllabus would be sufficient. However, the course requires a time commitment of 4 hours per week.

How can I ask my doubts?

We will have discussion forums where you can discuss the topics covered and ask doubts. Your peers or our Teaching assistants will answer the questions. Additionally, there will periodical video calls once a fortnight where instructors will answer questions. https://network.onefourthlabs.com

An IIT-M & IIM-A Incubated Company

Flash Sale : Limited time offer! | Offer ends in

Use Coupon Code: GET to get extra % Discount

Use coupon GET50 to get 50% offer on this course Bundle

Artificial Intelligence Combo Pack

Price :

199

Price :

799

Arun Prakash is the Founder & Chief Technology Officer of GUVI. He is a technologist with more than 17 years of experience. He has worked with bigwigs like Paypal, Symantec & Honeywell in the past.

How is this different from other courses?

Will I get a certificate on completing a course?

What are the pre-requisites?

How can I ask my doubts?