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:
- Understand core architecture of Deep Neural Networks
- Use TensorFlow and Keras
- Construct a computing environment and learn to install TensorFlow
- Develop TensorFlow graphs required for everyday computations
- Use logistic regression for classification along with TensorFlow
- Develop, design and train a multilayer neural network with TensorFlow
- Implement TensorFlow and Keras in Python
- Demonstrate Activation functions and Optimizers in detail with hands-on
- Demonstrate intuitively convolutional neural networks for image recognition
- Design and construct a neural network from simple to more accurate models
- Understand recurrent neural networks, its applications and learn how to build these solutions
- Learn how to build industry’s leading uses cases eg, Recommendation systems, Speech recognition, commercial grade Image classification and object localization etc.,
- Lead ML/DL projects
Pre-requisite
- Working Knowledge in Python
- Understanding of Machine Learning Models – Regression and Classification
- Working Knowledge of Python Machine Learning Module (scikit-learn)
Duration
3 days
Course Outline
- Introduction
- What is AI?
- Philosophy of AI
- Goals
- What contributes to AI?
- Programming without and with AI
- Applications of AI
- Types of Intelligence
- Agents and Environments
- Introduction
- Applications of ML
- Uses of ML
- Types
- Different Algorithms
- Central Tendency
- Why Python for ML?
- Anaconda – Overview and Installation
- Using Jupyter Notebook
- Variables
- Comprehension
- Functions and Modules
- Concept of Classes and Objects
- NumPy – Array manipulation
- Pandas – Data Analytics
- Matplotlib and Seaborn – Data Visualization
- Exploratory Data Analysis (EDA)
- Sklearn – Machine Learning (Regression and Classification)
- Introduction to Deep Learning
- Artificial Neural Networks
- Deep Neural Networks
- Convolutional Neural Networks (CNN)
- Deep Belief Networks (DBN)
- Generative Adversarial Networks (GANs)
- Recurrent Neural Networks (RNNs)
- Introduction to TensorFlow
- Graphs in TensorFlow
- A Simple TensorFlow Example
- Tensor Data Structures
- Placeholders
- Building Neural Networks using TensorFlow
- Introduction to Keras
- Keras Vs TensorFlow
- Advantages of Keras
- Installing Keras
- Keras Fundamentals
- Face Recognition Neural Networks with Keras
- Introduction to CNNs
- Architecture of CNN
- Basic Components
- The convolution operation
- The pooling operation
- Building CNN using TensorFlow
- Building CNN using Keras
- Introduction to TensorBoard
- Visualizing the Models using TensorBoard
- Using PyTorch Module
- Adding scalar and scalars
- Adding Image and Images
- Add Histogram
- What is NLP?
- What is NLTK?
- Components of NLP
- Download and Installation
- Tokenize Words and Sentences with NLTK
- POS Tagging and Chunking with NLTK
- Stemming and Lemmatization with NLTK
- Applications of NLP
- Text Summarization using NLP