Sunday, July 16, 2017

Part 8: Deep Learning

Deep Learning is the most exciting and powerful branch of Machine Learning.

Geoffrey Hinton is the god father of Deep Learning. Is a British-born Canadian cognitive psychologist and computer scientist, most noted for his work on Artificial Neural Networks. As of 2015 he divides his time working for Google and University of Toronto.

Deep Learning models can be used for a variety of complex tasks:
  1. Artificial Neural Networks for Regression and Classification
  2. Convolutional Neural Networks for Computer Vision
  3. Recurrent Neural Networks for Time Series Analysis
  4. Self Organizing Maps for Feature Extraction
  5. Deep Boltzmann Machines for Recommendation Systems
  6. Auto Encoders for Recommendation Systems
Here we'll cover first two:
  • Artificial Neural Networks for a Business Problem
  • Convolutional Neural Networks for a Computer Vision task

How Deep Learning Models are formed in Computer:

Our mind is a collection of billion-billion neurons, which take input from various sensors (eyes, nose etc) and process the input thru these neurons and generate output/decision.













Replication of above, is taken as below in computer to form Deep Learning Model.


















Hope this helps!!

Arun Manglick

No comments:

Post a Comment