A Look Into Neural Networks and Deep Reinforcement Learning

Artificial Neural Networks

Key Concepts of ANNs

Artificial Neural Network Elements

Neuron Vs Neural Network, by Brian Mwandau
Inputs are multiplied by corresponding weights to determine their relevance in reaching the correct output. The sum of these products is passed through an activation function to determine how far that signal should progress to affect the output, by Shibani Singh


  • input * weight = guess
  • real data - guess = error
  • error * weight’s contribution to error = adjustment

Gradient Descent

Types of Activation Functions

Binary Step Function

By Dishashree Gupta

Linear Function

By Dishashree Gupta

Sigmoid Function

By Dishashree Gupta

Tanh Function

By Dishashree Gupta

ReLU (Rectified Linear Unit)

By Dishashree Gupta

Convolutional Neural Networks

Regular 3 layer ANN, from CS231n
A CNN, with its arranged nodes in 3 dimension, each visualized by a layer, from CS231n

Convolutional Layers

By Thomas Wood
By Thomas Wood

An Example of a Convolution On An Image

By Thomas Wood
By Thomas Wood
By Thomas Wood

Applying Activation Functions

By Thomas Wood

Prerequisites To Deep Reinforcement Learning

Reinforcement Learning

The RL Learning Process

The subscripts denote the time steps t and t+1, which refer to different states, from KDnuggets

State-Action Pairs

Neural Networks and Deep Reinforcement Learning

By Pathmind

Case Study: DeepMind’s AlphaZero

AlphaZero could beat world champions in chess, shogi, and Go, by DeepMind Technologies




15 y/o that loves space, science, tech, and philosophy.

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

How to visualize the history of network learning: accuracy, loss in graphs.

Faster AI: Lesson 2 — TL;DR version of Fast.ai Part 1

Fellow humanist, come and join us in Natural Language Processing


Coupling Constant Prediction with Machine Learning

Convolutional Neural Networks and how its work

Inverse Tone Mapping using GANs

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Chloe Wang

Chloe Wang

15 y/o that loves space, science, tech, and philosophy.

More from Medium

When to Use Deep Learning

Creating a Reinforcement Learning Model with Tensorflow

Deep Q Learning, Monte Carlo Policy Gradients, Actor2Critic: from Conceptual to Math to Tensorflow

Implementing multi-armed bandits in reinforcement learning