Deep Learning with Python

Course Overview

  • Learn to implement Keras on top of TensorFlow to experiment with deep neural networks and tune machine learning models to produce more successful results with this course.
  •  
  •  Work on different types of Deep Architectures: Convolutional Networks, Recurrent Networks, and Autoencoders, and further get familiar with the advanced concepts of Natural Language Processing. Also, gain practical exposure on text summarization and processing.
  •  
  •  Our cloud labs comprise guided exercises practice building handwritten digit recognition, deep learning, convolution, and time-series models of Neural Networks. Gain hands-on experience by working with real-time uses cases and data sets using various neural network architecture, suitable to different industry domains and provide solutions

At the end of the training, participants will be able to:

  1. Understand core architecture of Deep Neural Networks
  2. Use TensorFlow and Keras
  3. Construct a computing environment and learn to install TensorFlow
  4. Develop TensorFlow graphs required for everyday computations
  5. Use logistic regression for classification along with TensorFlow
  6. Develop, design and train a multilayer neural network with TensorFlow
  7. Implement TensorFlow and Keras in Python
  8. Demonstrate Activation functions and Optimizers in detail with hands-on
  9. Demonstrate intuitively convolutional neural networks for image recognition
  10. Design and construct a neural network from simple to more accurate models
  11. Understand recurrent neural networks, its applications and learn how to build these solutions
  12. Learn how to build industry’s leading uses cases eg, Recommendation systems, Speech recognition, commercial grade Image classification and object localization etc.,
  13. Lead ML/DL projects

Pre-requisite

  1. Working Knowledge in Python
  2. Understanding of Machine Learning Models – Regression and Classification
  3. Working Knowledge of Python Machine Learning Module (scikit-learn)

Duration

3  days

Course Outline

  1. Introduction
  2. What is AI?
  3. Philosophy of AI
  4. Goals
  5. What contributes to AI?
  6. Programming without and with AI
  7. Applications of AI
  8. Types of Intelligence
  9. Agents and Environments
  1. Introduction
  2. Applications of ML
  3. Uses of ML
  4. Types
  5. Different Algorithms
  6. Central Tendency
  1. Why Python for ML?
  2. Anaconda – Overview and Installation
  3. Using Jupyter Notebook
  4. Variables
  5. Comprehension
  6. Functions and Modules
  7. Concept of Classes and Objects
  1. NumPy – Array manipulation
  2. Pandas – Data Analytics
  3. Matplotlib and Seaborn – Data Visualization
  4. Exploratory Data Analysis (EDA)
  5. Sklearn – Machine Learning (Regression and Classification)
  1. Introduction to Deep Learning
  2. Artificial Neural Networks
  3. Deep Neural Networks
  4. Convolutional Neural Networks (CNN)
  5. Deep Belief Networks (DBN)
  6. Generative Adversarial Networks (GANs)
  7. Recurrent Neural Networks (RNNs)
  1. Introduction to TensorFlow
  2. Graphs in TensorFlow
  3. A Simple TensorFlow Example
  4. Tensor Data Structures
  5. Placeholders
  6. Building Neural Networks using TensorFlow
  1. Introduction to Keras
  2. Keras Vs TensorFlow
  3. Advantages of Keras
  4. Installing Keras
  5. Keras Fundamentals
  6. Face Recognition Neural Networks with Keras
  1. Introduction to CNNs
  2. Architecture of CNN
  3. Basic Components
  4. The convolution operation
  5. The pooling operation
  6. Building CNN using TensorFlow
  7. Building CNN using Keras
  1. Introduction to TensorBoard
  2. Visualizing the Models using TensorBoard
  3. Using PyTorch Module
  4. Adding scalar and scalars
  5. Adding Image and Images
  6. Add Histogram
  1. What is NLP?
  2. What is NLTK?
  3. Components of NLP
  4. Download and Installation
  5. Tokenize Words and Sentences with NLTK
  6. POS Tagging and Chunking with NLTK
  7. Stemming and Lemmatization with NLTK
  8. Applications of NLP
  9. Text Summarization using NLP

Reviews