Deep Learning
Spread the love

Loading

Traditional pattern recognition models work with hand crafted features and relatively simple trainable classifiers.

There are many limitations with these techniques:

  • It is very tedious and costly to develop hand crafted features.
  • The hand-crafted features are usually highly dependent on one application, and can not be easily applied to other applications/problems. 
Feature extraction in classical machine learning
Figure : Feature extraction in classical machine learning

Deep learning has an inbuilt automatic multi stage feature learning process that learns rich  features.

Feature extraction in deep learning
Figure : Feature extraction in deep learning

Automatic feature extraction using deep learning
Figure : Automatic feature extraction using deep learning

Automatic feature extraction for images and text
Figure : Automatic feature extraction for images and text

By Hassan Amin

Dr. Syed Hassan Amin has done Ph.D. in Computer Science from Imperial College London, United Kingdom and MS in Computer System Engineering from GIKI, Pakistan. During PhD, he has worked on Image Processing, Computer Vision, and Machine Learning. He has done research and development in many areas including Urdu and local language Optical Character Recognition, Retail Analysis, Affiliate Marketing, Fraud Prediction, 3D reconstruction of face images from 2D images, and Retinal Image analysis in addition to other areas.