Certificate in Deep Learning with Python

Course details

Deep learning is a new superpower which will let you build AI systems that just weren't possible a few years ago. It's time to utilize intelligent automation to help your business grow, keep organized, and stay on top of the ;

Note: Please note that the course comes with online e-learning (videos) only. No hard copy will be provided.

Why should one take this certification?
Deep Learning is currently enabling numerous exciting applications in speech recognition, music synthesis, machine translation, natural language understanding, and many others. AI is transforming multiple industries.

After finishing this course, you will likely find creative ways to apply it to your work. We will help you master Deep Learning, understand how to apply it, and build a career in AI.

Who will benefit from taking this certification?
Job seekers looking for employment in various IT companies, PSUs or MNCs. Certification in Deep learning with Python framework benefits Data Science professionals, students and professionals across various Industries.
 
Benefits of Certification

• Government certification
• Certification valid for life
• Lifelong e-learning access
• Learning Hours: 12+ hrs

 
How It Works

1. Select Certification & Register
2. Receive Online e-Learning Access (LMS)
3. Take exam online anywhere, anytime
4. Get certified & Increase Employability

Test Details

• Duration: 60 minutes
• No. of questions: 50
• Maximum marks: 50, Passing marks: 25 (50%).
• There is NO negative marking in this module.
• Online exam.

 

TABLE OF CONTENTS

Module 1

UNDERSTANDING DEEP LEARNING

• The Course Overview
• A Brief History of Deep Learning
• Deep Learning Today
• Tools, Requirements, and Setup

BUILDING THE BASIC BLOCKS OF MACHINE LEARNING

• Exploring Supervised Learning
• Representational Learning and Feature Engineering
• Linear Regression
• The Perceptron

DIVING INTO DEEP NEURAL NETWORKS

• Feedforward Networks
• Backpropagation
• Neural Networks from Scratch
• Overfitting and Regularization

DISCOVERING CONVOLUTIONAL NEURAL NETWORKS (CNNS)

• Understanding CNNs
• Implementing a CNN
• Deep CNNs

USING CNNS TO SOLVE INCREASINGLY COMPLEX TASKS

• Very Deep CNNs
• Batch Normalization
• Fine-Tuning

LEARNING ABOUT DETECTION AND SEGMENTATION

• Semantic Segmentation
• Fully Convolutional Networks

EXPLORING RECURRENT NEURAL NETWORKS

• Recurrent Neural Networks
• LSTM and Advancements

OBJECT DETECTION USING CNNS

• Building a CNN to Detect General Images
• Training and Deploying on a Cluster

MOVING FORWARD WITH DEEP LEARNING AND AI

• Comparison of DL Frameworks
• Exciting Areas for Upcoming Research

 
Module 2

GETTING STARTED WITH DEEP LEARNING

• The Course Overview
• Fundamentals of Neural Networks
• Training Deep Neural Networks
• Using Forward Propagation, Backprop, and SGD
• Logistic Regression with a Neural Network Mindset
• Convolutional Neural Network Handwriting Recognition

DEEP MODELS WITH MXNET AND TENSORFLOW

• Working with MxNet and Gluon
• Defining and Training Neural Networks in MxNet/Gluon
• Working with TensorFlow and Keras
• Defining and Training Neural Networks in Keras/TensorFlow
• Comparing the Two Frameworks
• Mini Project - CIFAR Classification

IMPROVING DEEP NEURAL NETWORKS

• Weight Initialization for Deep Networks
• Regularization and Dropout
• Normalizing and Vanishing/Exploding Gradients
• Mini Project – SIGNS Dataset

OPTIMIZATION ALGORITHMS

• Understanding Stochastic Gradient Descent
• Adaptive Learning Algorithms - RMSProp and Adam
• Mini Project - Language Modeling

HYPERPARAMETER TUNING

• Hyperparameters
• Tuning Hyperparameters - Grid Search
• Tuning Hyperparameters - Random Search
• Mini Project -Music Synthesis

Updated on 04 June, 2024