About

This course teaches students how to build artificial neural networks and classify images, data, and sentiments using deep learning. Enrolling in this course also teaches prediction-making using linear regression, polynomial regression, and multivariate regression. 

Perfect for students looking to give their career shape as a Deep Learning Engineer!

Learn from the Best

Deep Learning Vipul Mishra

A self-motivated, innovative, hard-working, adaptable, and frugal person, Mr. Vipul Mishra holds expertise in Machine Learning, Embedded AI, and IoT for Smart Home. Smart City, Agriculture, Emerging Technologies and Architectural Synthesis (VLSI). His experience as an assistant professor and research scholar stretches back to 12+ years. His teaching experience sets him apart from other mentors for this course.

Course curriculum

    1. Introduction Video

      FREE PREVIEW

    2. Introduction

      FREE PREVIEW

    3. Course Instructions - Vipul Mishra

    1. Introduction of Deep Learning

    2. Introduction of AI and ML

    3. Artificial Neural Networks and comparison between AI, ML and DL

    4. Machine Learning: Linear and non Linear problems

    5. Features and Weights, Linear Regression, Logistic Regression

    6. Forward and Backward Propagation

    7. Activation Functions and Bias

    8. Training of Neural Network: Derivatives and linear Regression

    9. Training of Neural Network: Loss Functions

    10. Training of Neural Network: Gradient Descent

    11. Training of Neural Network: Logistics Regression, Representation, Forward and Backward Function

    12. Multiclass Classification 1

    13. Multiclass Classification 2

    1. Overview of (Dataset, Regularization and Hyperparameter Tuning)

    2. Dataset splitting and distribution.

    3. Importance of choosing Development and Test sets wisely

    4. Evaluation Metrics

    5. Using of a single Evaluation Metrics

    6. Optimizing Metrics

    7. False Positive and False Negative Metrics

    8. Bias vs Variance

    9. High Bias and High Variance

    10. How we can compare the performance of our system?

    11. Regularization: L1/L2 regularization

    12. Dropout Regularization and Early Stopping

    13. Data Augmentation

    14. Normalizing Data Sets

    15. Vanishing and Exploding Gradients

    16. Batch vs. mini-batch Gradient descent

    17. Exponentially weighted averages and Momentum

    18. RMS Prop and Adam Optimization Algorithm

    19. How to try Hyperparameter

    20. Hyperparameter Models

    21. quiz - 1

    22. Course Instructions - Vipul Mishra

    1. Convolutional Neural Networks

    2. Why do we require CNN?

    3. ANN vs CNN

    4. Convolutional and how we can share the weights

    5. Padding

    6. Stride, Channel and Pooling

    7. Some famous Neural Networks and how to utilize them

    8. Some famous Neural Networks and how to utilize them part 2

    9. Transfer Learning introduction

    10. Transfer Learning concept

    11. Object localization and detection

    12. R-CNN method

    13. YOLO Object Detection

    14. YOLO Classification and Detection, Residual Block

    15. Segmentation

    16. Segmentation and Summary

    1. Recurrent Neural Networks

    2. Recurrent Neural Networks

    3. Three views of NLP and associated challenges

    4. Representation in Distributed and Discrete manner

    5. Preparation and process of Word Embeddings

    6. Name entity recognition problem

    7. Language Models

    8. Vanishing Gradient on RNN-LM, LSTM and GRU

    9. Attention

    10. Quiz - 2

    11. FINAL EXAMINATION (DEEP LEARNING)

    12. Feedback - Compulsory

About this course

  • 66 lessons
  • 6.5 hours of video content

What You'll Learn

Introduction to AI and Deep Learning

  • Motivation: Foundations and Terminology of Deep Learning

  • AI vs ML vs DL: A comparison

  • Features and Weights.

  • Machine Learning Recap: Linear Regression, Logistic Regression

  • Activation Functions

  • Hands-on: Introduction to Python Programming


Neural Networks

  • Neural Networks

  • Loss Functions

  • Gradient Descent

  • Feedforward and Backward Propagation

  • Deep Learning Model training

  • Hands-on: Building Neural Networks


Dataset, Regularization and Hyperparameter Tuning

  • Dataset splitting and distribution. 

  • Evaluation Metrics

  • Bias vs Variance

  • Regularization: L1/L2 regularization, Dropout, Early Stopping

  • Optimization methods

  • Hyperparameter Tuning

  • Hands-on: Tuning Neural Networks


Convolutional Neural Networks

  • ANN vs CNN

  • Convolution, pooling, padding, striding

  • Transfer Learning 

  • Applications of CNN

  • Hands-on: Image Classification using CNN


Recurrent Neural Networks

  • ANN vs RNN

  • Sequential Processing with RNN

  • Forward and Back Propagation

  • Language Models

  • LSTM and GRU

  • RNN Applications

  • Hands-on: Text Classification using RNN

What this Course Includes

  • 59 videos
  • 7 hours of on-demand video
  • 2 Quizzes and 1 final paper
  • 1 Real-Life Projects 
  • Access on mobile, Laptop, and TV
  • Lifetime access to videos anytime, anywhere
  • Certificate of completion by Skillarena 
  • Guaranteed Internship

Requirements

  • Willingness to Learn and Explore