Machine Learning Gallery

AD

Developed by Akhil Devarashetti

Deep Learning Engineer | akhil.ai

This is a master project of some experiments with Neural Networks. Every project here is runnable, visualized and explained clearly.

Take a tour

The Basics

Start your Deep Learning journey with simple problems

RegressionClassification
Start with basics

Learn a Line

Train a neuron to learn line equation

Computer Vision

Visualize and learn Computer Vision models from basic classifiers to complex vision problems

ClassificationDetectionCaptioningGANs
Start here

Learn how neural networks are trained on text

RNNsEmbeddingsAttention
Get started

Reinforcement Learning

Learn how models are trained to play games from basic to state-of-the-art methods

  • Policy Gradients
  • Deep Q
  • MCTS
  • AlphaZero
  • MuZero
Get started

Unpublished Papers

  • DisCease: Evolving Social Distancing And Herd Immunity

    Abstract: I tried to create a model that simulates the spread of a disease that does not have a medicine. I observed the effects of varying parameters, then introduced a concept of deflections which mimic social distancing and social gatherings. I finally made an attempt to evolve these deflections based on a performance metric.

    ReadRun
    DisCease: Evolving Social Distancing And Herd ImmunityImage
  • A Brief Survey of Model-Free Deep Reinforcement Learning

    Abstract: Deep Reinforcement Learning is a branch of machine learning techniques that is used to find out the best possible path given a situation. It is an interesting domain of algorithms ranging from basic multi-arm bandit problems to playing complex games like Dota 2. This paper surveys the research work on model-free approaches to deep reinforcement learning like Deep Q Learning, Policy Gradients, Actor-Critic methods and other recent advancements.

    A Brief Survey of Model-Free Deep Reinforcement LearningImage

More to come

Computer Vision

  • Find All Numbers

  • Dense Cap

  • MNIST GAN

  • Attention, Attention!

  • Style, Please

  • Style, Please V2

Natural Language Processing

  • What Genre - Attention

  • Segment Highlighter

  • Action Assistant

  • Next Sentence

Reinforcement Learning

  • Dodger

Unsupervised Learning

  • AutoEncoder

  • Self-Organizing Feature Maps

  • Memorize Please

Miscellaneous

  • Spiking Neurons

  • MNIST Detection Dataset

ML Gallery