Deep Learning for Beginners

Introduction:

Embark on your AI journey with our beginner-friendly course using Deep Learning Studio by Deep Cognition. Dive into the world of AI development and deployment, leveraging the first-of-its-kind robust deep learning platform with a user-friendly visual interface. This comprehensive course covers data ingestion, model development, training, deployment, and management, providing you with valuable insights related to AI. With seamless integration with TensorFlow, MXNet, and Keras, our easy-to-use drag-and-drop editor allows you to learn and build deep learning models without the need for extensive coding. Elevate your AI skills with us!

Course Objectives:

  • Machine Learning
  • Deep Learning
  • Deep Learning Studio
  • Handwritten Digit Classification
  • Image Classification
  • Sentimental Analysis
  • Topic Modelling

Duration

7 hours, 1 Day Course

Mode of Delivery

Classroom-based, Instructor-led Training

Course Outlines

  1. Overview of Machine Learning and Deep Learning
    1. What is Machine Learning?
    2. Real Life Applications of Machine Learning
    3. Types of Machine Learning
    4. What is Neural Network
    5. What is Deep Learning
    6. Machine Learning vs Deep Learning
  2. Deep Learning Studio Desktop
    1. Install Deep Learning Studio Desktop
    2. Exploring Deep Learning Studio Desktop Interface
  3. Handwritten Digit Classification
    1. MNIST Handwritten Digit Dataset
    2. MNIST Classification with Feedforward Neural Network
    3. What is Convolutional Neural Network (CNN)
    4. MNIST Classification with CNN
  4. Image Classification
    1. CIFAR10 Image Dataset
    2. CIFAR10 Classification with Feedforward Neural Network
    3. CIFAR10 Classification with CNN
  5. Sentimental Analysis
    1. IMDB Movie Review Dataset
    2. What is Recurrent Neural Network (RNN)
    3. What is Long Short Term Memory (LSTM)
    4. IMDB Sentimental Analysis with LSTM RNN
  6. Topic Modelling
    1. Reuters Newswire Dataset
    2. Reuters Topic Modelling with LSTM RNN