Certified Deep
Learning Professional
 
Master Deep Learning to step up your Machine Learning career.
 
6 Days / 48 Hours / 19 Modules
+ 3 month coaching + 1 year eLearning access
funding-schemes sbl-khas-black-centered
Get in Touch With Us
Certified Deep
Learning
Professional
Master Deep Learning
to step up your
Machine Learning career.


6 Days / 48 Hours / 10 Modules
+ 3 month coaching + 1 year eLearning access
funding-schemes-sbl-khas-white-centered
Master Deep Learning and step up your machine learning career
The Certified Deep Learning Professional qualification is course is a steppingstone in Data Science journey using which the participants will enable the candidate to learn deep learning techniques with industry best practices.

Duration

6 days / 48 hours

Level

Intermediate to Advanced

Delivery

100% Online - Instructor Led
  • Course Code

    ML104
  • Audience

    Anyone with interest in Machine Learning And Python
  • Language

    English
  • Certification

    Awarded by ICTC
 
Key Learning Outcomes

This course will also give students a chance to understand the fundamental issues and challenges of machine learning which include data, model selection, and model complexity. This course will equip you with the necessary skills needed to excel in this field. By the end of the training program, you will be able to:
  • Become familiar with various neural networks.
  • Utilize Keras and TFLearn APIs to form models and implement them.
  • Form a good understanding of Artificial Intelligence.
  • Become familiar with dynamic programming.
  • Gain understanding of Temporal Difference Learning
 
 
Key Learning Outcomes

This course will also give students a chance to understand the fundamental issues and challenges of machine learning which include data, model selection, and model complexity. This course will equip you with the necessary skills needed to excel in this field. By the end of the training program, you will be able to:
  • Become familiar with analyzing data, computing statistical measures along with Data Wrangling, Data Cleansing, Data Manipulation, etc.
  • Become familiar with Machine Learning algorithms including Black Box techniques such as Neural Networks and Support Vector Machine.
  • Become familiar with Regression algorithms and the application of Python as statistical software in Machine Learning and Data Science.
  • Build predictive models.
  • Be able to create Data Visualization, Data Manipulation in different forms and draw meaningful business insights from the underlying data.
 
Program Curriculum
Module 1 - Introduction to Deep Learning

Introduction to Deep Learning

  1. Deep Learning: A revolution in Artificial Intelligence
  2. Limitations of Machine Learning
  3. What is Deep Learning
  4. Advantage of Deep Learning over Machine Learning
  5. 3 Reasons to go for Deep Learning
  6. Real-Life use cases of Deep Learning
  7. Review of Machine Learning
Module 2 - Understanding Neural Networks with TensorFlow

Understanding Neural Networks with TensorFlow

  1. How Deep Learning Works
  2. Activation Functions
  3. Illustration Perceptron
  4. Training a Perceptron
  5. Important parameters of Perceptron
  6. What is TensorFlow
  7. TensorFlow code-basics
  8. Graph Visualization
  9. Constants, Placeholders, Variables
  10. Creating a Model
Module 3 - Deep dive into Neural Networks with TensorFlow

Deep dive into Neural Networks with TensorFlow

  1. Understand limitations of a Single Perceptron
  2. Understand Neural Networks in Detail
  3. Illustrate Multi-Layer Perceptron
  4. Backpropagation – Learning Algorithm
  5. Understand Backpropagation – Using Neural Network Example
  6. MLP Digit-Classifier using TensorFlow
  7. TensorBoard
Module 4 - Master Deep Networks

Master Deep Networks

  1. Why Deep Networks
  2. Why Deep Networks give better accuracy?
  3. Use-Case Implementation on SONAR dataset
  4. Understand How Deep Network Works?
  5. How Backpropagation Works?
  6. Illustrate Forward pass, Backward pass
  7. Different variants of Gradient Descent
  8. Types of Deep Networks
Module 5 - Convolutional Neural Networks (CNN)

Convolutional Neural Networks (CNN)

  1. Introduction to CNNs
  2. CNNs Application
  3. Architecture of a CNN
  4. Convolution and Pooling layers in a CNN
  5. Understanding and Visualizing a CNN
Module 6 - Recurrent Neural Networks (RNN)

Recurrent Neural Networks (RNN)

  1. Introduction to RNN Model
  2. Application use cases of RNN
  3. Modelling sequences
  4. Training RNNs with Backpropagation
  5. Long Short-Term memory (LSTM)
  6. Recursive Neural Tensor Network Theory
  7. Recurrent Neural Network Model
Module 7 - Restricted Boltzmann Machine (RBM) and Autoencoders

Restricted Boltzmann Machine (RBM) and Autoencoders

  1. Restricted Boltzmann Machine
  2. Applications of RBM
  3. Collaborative Filtering with RBM
  4. Introduction to Autoencoders
  5. Autoencoders applications
  6. Understanding Autoencoders
Module 8 - Keras API

Keras API

  1. Define Keras
  2. How to compose Models in Keras
  3. Sequential Composition
  4. Functional Composition
  5. Predefined Neural Network Layers
  6. What is Batch Normalization
  7. Saving and Loading a model with Keras
  8. Customizing the Training Process
  9. Using TensorBoard with Keras
  10. Use-Case Implementation with Keras
Module 9 - TFLearn API

TFLearn API

  1. Define TFLearn
  2. Composing Models in TFLearn
  3. Sequential Composition
  4. Functional Composition
  5. Predefined Neural Network Layers
  6. What is Batch Normalization
  7. Saving and Loading a model with TFLearn
  8. Customizing the Training Process
  9. Using TensorBoard with TFLearn
  10. Use-Case Implementation with TFLearn
Module 10 - Artificial Intelligence

Artificial Intelligence

  1. Introduction
  2. Course Outline and Big Picture
  3. Where to get the Code
  4. How to Succeed in this Course
  5. Warmup
Module 11 - Return of the Multi-Armed Bandit

Return of the Multi-Armed Bandit

  1. Section Introduction: The Explore-Exploit Dilemma
  2. Applications of the Explore-Exploit Dilemma
  3. Epsilon-Greedy
  4. Updating a Sample Mean
  5. Designing Your Bandit Program
  6. Comparing Different Epsilons
  7. Optimistic Initial Values
  8. UCB1
  9. Bayesian / Thompson Sampling
  10. Thompson Sampling vs. Epsilon-Greedy vs. Optimistic Initial Values vs. UCB1
  11. Nonstationary Bandits
  12. Bandit Summary, Real Data, and Online Learning
Module 12 - High Level Overview of Reinforcement Learning

High Level Overview of Reinforcement Learning

  1. What is Reinforcement Learning?
  2. On Unusual or Unexpected Strategies of RL
  3. Defining Some Terms
Module 13 - Build an Intelligent Tic-Tac-Toe Agent

Build an Intelligent Tic-Tac-Toe Agent

  1. Naive Solution to Tic-Tac-Toe
  2. Components of a Reinforcement Learning System
  3. The Value Function and Your First Reinforcement Learning Algorithm
  4. Tic Tac Toe Code: Outline
  5. Tic Tac Toe Code: Representing States
  6. Tic Tac Toe Code: Enumerating States Recursively
  7. Tic Tac Toe Code: The Environment
  8. Tic Tac Toe Code: The Agent
  9. Tic Tac Toe Code: Main Loop and Demo
Module 14 - Markov Decision Processes

Markov Decision Processes

  1. Gridworld
  2. The Markov Property
  3. Defining and Formalizing the MDP
  4. Future Rewards
  5. Value Function Introduction
  6. Value Functions
  7. Bellman Examples
  8. Optimal Policy and Optimal Value Function
  9. MDP Summary
Module 15 - Dynamic Programming

Dynamic Programming

  1. Intro to Dynamic Programming and Iterative Policy Evaluation
  2. Gridworld in Code
  3. Designing Your RL Program
  4. Iterative Policy Evaluation in Code
  5. Policy Improvement
  6. Value Functions
  7. Policy Iteration in Code
  8. Policy Iteration in Windy Gridworld
  9. Value Iteration
  10. Value Iteration in Code
  11. Dynamic Programming Summary
Module 16 - Monte Carlo

Monte Carlo

  1. Monte Carlo Intro
  2. Monte Carlo Policy Evaluation
  3. Monte Carlo Policy Evaluation in Code
  4. Policy Evaluation in Windy Gridworld
  5. Monte Carlo Control
  6. Monte Carlo Control in Code
  7. Monte Carlo Control without Exploring Starts
  8. Monte Carlo Control without Exploring Starts in Code
  9. Monte Carlo Summary
Module 17 - Temporal Difference Learning

Temporal Difference Learning

  1. Temporal Difference Intro
  2. TD(0) Prediction in Code
  3. SARSA
  4. SARSA in Code
  5. Q Learning
  6. Q Learning in Code
  7. TD Summary
Module 18 - Approximation Methods

Approximation Methods

  1. Approximation Intro
  2. Linear Models for Reinforcement Learning
  3. Features
  4. Monte Carlo Prediction with Approximation
  5. Monte Carlo Prediction with Approximation in Code
  6. TD(0) Semi-Gradient Prediction
  7. Semi-Gradient SARSA
  8. Semi-Gradient SARSA in Code
  9. Course Summary and Next Steps
Module 19 - Stock Trading Project with Reinforcement Learning

Stock Trading Project with Reinforcement Learning

  1. Stock Trading Project Section Introduction
  2. Data and Environment
  3. How to Model Q for Q-Learning
  4. Design of the Program
  5. Code
  6. Stock Trading Project Discussion

Key Features

  • Personalized Study Resources
  • Real-world workshop based learning
  • Quality self-paced videos
  • Interactive Learning
  • Sharable digital badge

Pre-Requisites

  • Analytical Mindset
  • Willingness to self learn online
  • No prior experience is required
  • We will start from the very basics
  • Committed to complete all tasks

Who Should Join

  • Professional switching careers
  • Machine learning practitioners looking to expand their skillset
  • New Programmers
  • Anyone interested in Machine Learning
Program Key Highlights
online-learning-2
40 hours of Remote Online Learning
learning-hours
80 Additional Self Learning Hours
hands-on
12 Live Hands-on Projects
certification
Certified by International Body
mentor
Mentorship with Industry Experts
industry
Designed for Beginners & Professionals
Request for more Information

    python-cert
    Get Professionally Certified
    Upon successfully completing this program, participants will be awarded the Professional Certification in Python Data Science by International Council for Technology Certifications (ICTC).
    This award is a validation to the efforts taken to master the domain expertise that will set you apart from your competition.
    Be a part of the global network of data science professionals and join the community across sectors.
     
     



    Join Us For Our Next Program
    And step up your Machine Learning Career
    *Payments are only accepted once applicants are enrolled into the program.*
    Contact us on Whatsapp for more enquiries