Deep Learning AI with Python
Abdur Rahman (Joy)

Abdur Rahman (Joy)

View Profile

Deep Learning AI with Python

Online: TK 5000

Start Date : 2020-09-05  
End Date : 2020-11-05

Total Class : 15   Total Hours: 45

Location : D F Tower (Level-11A) Skill Jobs Digital Lab Skill Jobs Digital Lab, House # 11 (Level-11A), Road # 14, Dhanmondi, Shobhanbag, Dhaka-1209

Registration Now

AI and Deep Learning courses offer practical and task-oriented training using TensorFlow and Keras on the Python platform. Recent developments in Deep learning have been nothing short of a revolution and have enabled some of the most exciting and powerful applications in the field of Artificial Intelligence.  

This is a specialization course that will help you to get a break into the AI and Deep Learning domain, with one of the most sought-after skills. You will learn the foundations of Deep Learning, understand how to build neural networks, and learn how to build successful Deep Learning-based AI projects using Tensor Flow and Keras. You will work on case studies on computer vision, text data processing, Image processing, Speech analytics - Speech to text / Voice tonality. After successful completion of this course, you will master not only the theory but also learn how it is applied in the industry.

 

Who Should do this course?

Analytics professionals or aspirants with prior working knowledge of Data Science with Python, who are looking Deep Learning certification to up-skill with the practical application of AI Deep Learning with TensorFlow and Keras.

Considering the practical application-based curriculum, this is the best Deep Learning training course in Bangladesh for Data Science professionals who are looking for an industry-relevant certification from an eminent Deep Learning Institute. 

 

Course Content

INTRODUCTION TO DEEP LEARNING

  • What are the Limitations of Machine Learning?
  • What is Deep Learning?
  • Advantage of Deep Learning over Machine learning
  • Reasons to go for Deep Learning
  • Real-Life use cases of Deep Learning

 

  INTRODUCTION TO ARTIFICIAL INTELLIGENCE (AI)

  • History of AI
  • The modern era of AI
  • How is this era of AI different?
  • Transformative Changes
  • Role of Machine learning & Deep Learning in AI
  • Hardware for AI (CPU vs. GPU vs. TPU)
  • Software Frameworks for AI
  • Deep Learning Frameworks for AI
  • Key Industry applications of AI

DEEP LEARNING IN PYTHON

  • Overview of important python packages for Deep Learning

OVERVIEW OF TENSOR FLOW

  • What is Tensor Flow?
  • Tensor Flow code-basics
  • Graph Visualization
  • Constants, Placeholders, Variables
  • Tensorflow Basic Operations
  • Linear Regression with Tensor Flow
  • Logistic Regression with Tensor Flow
  • K Nearest Neighbor algorithm with Tensor Flow
  • K-Means classifier with Tensor Flow
  • Random Forest classifier with Tensor Flow

NEURAL NETWORKS USING TENSOR FLOW

  • A quick recap of Neural Networks
  • Activation Functions, hidden layers, hidden units
  • Illustrate & Training a Perceptron
  • Important Parameters of Perceptron
  • Understand limitations of A Single Layer Perceptron
  • Illustrate Multi-Layer Perceptron
  • Back-propagation – Learning Algorithm
  • Understand Back-propagation – Using Neural Network Example
  • TensorBoard

DEEP LEARNING NETWORKS

  • What is Deep Learning Networks?
  • Why Deep Learning Networks?
  • How Deep Learning Works?
  • Feature Extraction
  • Working of Deep Network
  • Training using Backpropagation
  • Variants of Gradient Descent
  • Types of Deep Networks
  • Feedforward neural networks (FNN)
  • Convolutional neural networks (CNN)
  • Recurrent Neural networks (RNN)
  • Generative Adversal Neural Networks (GAN)
  • Restrict Boltzmann Machine (RBM)

  CONVOLUTIONAL NEURAL NETWORKS (CNN)

  • Introduction to Convolutional Neural Networks
  • CNN Applications
  • The architecture of a Convolutional Neural Network
  • Convolution and Pooling layers in a CNN
  • Understanding and Visualizing a CNN
  • Transfer Learning and Fine-tuning Convolutional Neural Networks

RECURRENT NEURAL NETWORKS (RNN)

  • Intro to RNN Model
  • Application use cases of RNN
  • Modeling sequences
  • Training RNNs with Backpropagation
  • Long Short-Term Memory (LSTM)
  • Recursive Neural Tensor Network Theory
  • Recurrent Neural Network Model

  RESTRICTED BOLTZMANN MACHINE (RBM)

  • What is a Restricted Boltzmann Machine?
  • Applications of RBM
  • Collaborative Filtering with RBM
  • Introduction to Autoencoders & Applications
  • Understanding Autoencoders

  DEEP LEARNING WITH TFLEARN

  • Define TFlearn
  • Composing Models in TFlearn
  • Sequential Composition
  • Functional Composition
  • Predefined Neural Network Layers
  • What is Batch Normalization
  • Saving and Loading a model with TFlearn
  • Customizing the Training Process
  • Using TensorBoard with TFlearn
  • Use-Case Implementation with TFlearn

  DEEP LEARNING WITH KERAS

  • Define Keras
  • How to compose Models in Keras
  • Sequential Composition
  • Functional Composition
  • Predefined Neural Network Layers
  • What is Batch Normalization
  • Saving and Loading a model with Keras
  • Customizing the Training Process
  • Using TensorBoard with Keras
  • Use-Case Implementation with Keras
  • Intuitively building networks with Keras

  KEY APPLICATIONS OF DEEP LEARNING IN AI

  • Computer Vision
  • Text Data Processing
  • Image processing
  • Audio & Video Analytics
  • Internet of things (IoT)

  FINAL PROJECTS- CONSOLIDATE THE LEARNING & IMPLEMENT THEM IN PYTHON

  • Computer Vision
  • Text Data Processing
  • Image processing - PNG, PDF, JPEG, JPG, etc.
  • Speech analytics - Speech to text / Voice tonality