Deep Cognition University

Deep Cognition University
Deep Cognition University 2019-07-10T06:33:41+00:00

Attend our Pragmatic Trainings on Deep Learning using Deep Cognition

Comprehensive hands-on training for professionals and students from Deep Learning Practitioners
    Deep Learning using Deep Cognition - [Enroll Now]
        - Theory in Deep Neural Networks
        - Familiarization with Deep Cognition Studio and Best Practices
        - Architectural Design using AutoML
        - Deep Learning Models
        - Hands-on Exercises

Modes of Delivery:
    - Virtual Classroom Training
    - In-Person Training

    1. High school level calculus and linear algebra 
    2. Deep Learning Studio Software running on a computer 
    1. To give gentle introduction to theory of deep artificial neural networks
    2. To get familiar with Deep Cognition Studio 
    3. To design architecture using AutoML
    4. To deploy and monitor Deep Learning Models
    5. Give practical working knowledge of deep neural networks. 
    6. At the end of the courses students should be able to design and train following types of neural networks on practical problems:
        a. Fully Connected Nets for numeric data analysis
        b. Convolutional Neural Networks for image classification
        c. RNN for Temporal Data
Duration: 2 Day
    1. Introduction 
        1. Introduction to Artificial Intelligence and Machine Learning
        2. Why Deep Learning is relevant today
        3. What is required to learn Deep Learning?
        4. Introduction to Deep Cognition Studio
        5. Lab: Experiencing first Deep Neural Network 
        6. Introduction to Neural Network
        7. Types of Neural Networks
        8. Types of Deep Learning models: supervised, unsupervised and reinforcement learning
    2. Delving Deep into Deep Cognition Studio 
        2.1 Multilayer Perceptron in Deep Cognition Studio 
            1. Binary Classification with Neural Networks
            2. First deep learning model for binary classification
            3. Logistic Regression with Neural Networks
            4. Deep learning model for logistic regression
            5. Activation Functions
            6. Importance of non-linear activation
            7. Data encoding for deep neural networks
            8. Lab: Developing Digit Recognition Neural Network
        2.2 Convolution Neural Network in Deep Cognition Studio
            1. Convolutional Neural Networks
            2. Components of CNN
            3. Data augmentation 
            4. Transfer learning for using pre-trained networks
            5. NN Architecture: VGG
            6. Lab: Face Detection 
            7. Lab: Emotion Analysis 
            8. Lab: Sentiment Analysis using RNN Network

        2.3 Recurrent Neural Network in Deep Cognition Studio 
            1. Recurrent Neural Network
            2. Long Short-Term Memory (LSTM)
            3. Word Embedding
            4. Lab: Sentiment Analysis using RNN Network

Enroll Now

Deep Cognition’s Announcements

Deep Learning Studio 3.0 Now Live!
Download now!



  • 8330, Sterling Street, Irving, TX, USA 75063
  • +1-214-441-3517