Inputs -> Numerical encoding -> Learn representation (patterns/feature/weights) -> Representation outputs -> Outputs

Anatomy of Neural Network

  • Input Layers
  • Hidden Layers
  • Output Layers

Type of Learning

  • Supervised Learning.
  • Semi-Supervised Learning.
  • Unsupervised Learning.
  • Transfer Learning.
  • Reinforcement Learning.

What is deep learning actually used for?

Deep learning is for making neural network for neural network and making in the working.

Deep Learning some use cases

  • Recommendation.
  • Translation. [Sequence to Sequence (seq2seq)].
  • Speech Recognition.
  • Computer Vision.
  • Natural Language Processing (NPL) [Classification | Regression].

What is and why use Tensorflow?

  • End-to-End platform for machine learning
  • Write fast deep leaning code in Python/other accessible languages(able to run on a GPU/TPU)
  • Able to access many pre-built deep learning models(TensorFlow Hub)
  • Whole stack: preprocess data, model data, deploy model in your application.
  • Originally designed and used in house by Google ( now open - source)

What is a Tensor?

A tensor is an algebraic object that describes a multilinear relationship between sets of algebraic objects related to a vector space.