• No products in the cart.

ratings 

Transfer learning is a research problem in machine learning that focuses on storing knowledge gained while solving one problem and applying it to a unlike but linked problem.

PRIVATE
Course Access

Unlimited Duration

Last Updated

July 29, 2021

Students Enrolled

20

Total Reviews

Posted by
Certification

Transfer learning is a learning technique that reuses parts of a previously trained model on a new network tasked for a different but similar problem. In transfer learning, we try to transfer as much knowledge as possible from the previous task the model was trained on to the new task. Transfer learning is useful when you have deficient data for a new field you want handled by a neural network and there is a big pre-existing data that can be transferred to your problem. Transfer learning has many benefits but the important advantages are saving training time, not needing a lot of data and better performance of neural networks. It has helped computers solve these and many other complicated problems. Like we humans have an ability to transfer our knowledge across different tasks, the more related the task, the easier it is for us to transfer our knowledge.  

Course Curriculum

    • What is Convolution operation in CNN 00:00:00
    • Padding in CNN 00:00:00
    • Operation of CNN 00:00:00
    • Max Pooling Layer in CNN 00:00:00
    • Flattening Layer followed by ANN 00:00:00
    • Hands on Practical Implementation 00:00:00
    • AlexNet Architecture 00:00:00
    • Why does AlexNet achieve better results 00:00:00
    • Why does AlexNet achieve better results 00:00:00
    • Hands on Practical Implementation 00:00:00
    • Architecture of LeNet 00:00:00
    • In-depth Intuition of LeNet 00:00:00
    • Summary 00:00:00
    • Hands on practical implementation 00:00:00
    • Introduction 00:00:00
    • The Network Structure 00:00:00
    • Network Configuration 00:00:00
    • Training 00:00:00
    • Summary of VGGNet improvement points 00:00:00
    • Hands on Implementation of VGGNet 00:00:00
    • Introduction 00:00:00
    • The problem caused by increasing depth 00:00:00
    • Degradation of deep network 00:00:00
    • Deep Residual Networks 00:00:00
    • Different Variants of ResNet 00:00:00
    • Hands on Implementation of ResNet 00:00:00
    • Introduction 00:00:00
    • Four Parallel Channels 00:00:00
    • Complete Network design 00:00:00
    • Training Methodology 00:00:00
    • Inception-V2(2015) 00:00:00
    • Inception-V3(2015) 00:00:00
    • Factorizing Convolutions with Large Filter Size 00:00:00
    • Spatial Factorization into Asymmetric Convolutions 00:00:00
    • Inception-V4-2016 00:00:00
    • Residual Inception Blocks 00:00:00
    • Scaling of the Residuals 00:00:00
    • Conclusion 00:00:00
    • Summary 00:00:00
    • Hands on Implementation of ResNet 00:00:00

    Course Reviews

    Profile Photo
    4 4
    1932

    Students

    About Instructor

    Course Events

    [wplms_eventon_events]

    More Courses by Insturctor

    © 2021 Ernesto.  All rights reserved.  
    X