Code Monkey home page Code Monkey logo

Manish Chumun's Projects

autoencoder icon autoencoder

Examples of Autoencoders (simple and convolutional) using MNIST dataset

face_generation icon face_generation

This is my project submission for the Deep Learning Foundation Nanodegree from Udacity. In this project, I use a generative adversarial network (GAN) to generate new images of faces.

image-classification icon image-classification

A convolution network to classify images from the CIFAR-10 dataset. The dataset consists of airplanes, dogs, cats, and other objects. The dataset was preprocessed, then a convolutional neural network on all the samples was trained. Includes normalization of the images, one-hot encode the labels, build a convolutional layer, max pool layer, and fully connected layer.

intro-to-tensorflow icon intro-to-tensorflow

This was part of Deep Learning Foundation Nanodegree Course with Udacity. Here I create a simple single layer neural network in Tensorflow. I implement data normalisation and then build and train the network with Tensorflow.

language_translation icon language_translation

This is my project submission for the Deep Learning Foundation Nanodegree from Udacity. In this project, I use a Recurrent Neural Network (RNN) to train a sequence to sequence model on a dataset of English and French sentences that can translate new sentences from English to French.

learn_math_fast icon learn_math_fast

This is the Curriculum for "How to Learn Mathematics Fast" By Siraj Raval on Youtube

machine-learning-coursera icon machine-learning-coursera

The repo contains my work from the Machine Learning course taught by Andrew Ng on Coursera. Each folder in turn contains the assignments and submissions that were part of the course.

my_first_neural_network icon my_first_neural_network

Udacity Deep mind assignment. Building a simple neural network for predicting bike sharing rides from a real dataset

tv-script-generation icon tv-script-generation

This is my project submission for the Deep Learning Foundation Nanodegree from Udacity. In this project, I generate your own Simpsons TV scripts using RNNs. I use part of the Simpsons dataset of scripts from 27 seasons. The Neural Network built generate a new TV script for a scene at Moe's Tavern.

weight_initialisation icon weight_initialisation

The notebook analyses the effect on initialising weights with good and bad values. Initialising weights with good values can help a neutral network arrive at the optimal solution quicker. This notebook was used for explaining the importance of proper weight initialisation in my Udacity Deep Learning Foundation Nanodegree.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.