Introduction

• dealing with algorithms inspired by the structure and function of the brain called artificial neural networks

  

• similar to how nervous system structured where each neuron connected each other and passing information

Deep Convolutional Neural Networks (ConvNets)

• deep artificial neural networks used:
  • to classify images (e.g. name what they see)
  • cluster them by similarity (photo search)
  • perform object recognition within scenes
• algorithms that can identify faces, individuals, street signs, tumors, perform optical character recognition (OCR)
• pre-processing required is much lower as compared to other classification algorithms
• architecture of a ConvNet is analogous to that of the connectivity pattern of Neurons in the Human Brain - Visual Cortex
• captures the spatial and temporal dependencies in an image

Tensors

An nth - rank tensor in m-dimensional space is a mathematical object that has n indices and m^n components and obeys certain transformation rules.

• generalizations of scalars, vectors, and matrices to an arbitrary number of indices
• used in physics such as elasticity, fluid mechanics, and general relativity

Notations

Images as tensors

Convolution

Operation