jasonx1011 Goto Github PK
Name: Jason
Type: User
Name: Jason
Type: User
[Numpy] Bike-Sharing Prediction using Feedforward Neural Networks (FNNs); Implemented MLP, SGD and backpropagation using Numpy to predict daily ridership, validation loss (MSE) = 0.14
[TensorFlow] Designed the Multi-Periodic Activation Layer of FNNs and CNNs in Image Classification
Repo for the Deep Learning Nanodegree Foundations program.
Re-implement CVPR2017 paper: "dense captioning with joint inference and visual context" and minor changes in Tensorflow. (mAP 8.296 after 500k iters of training)
End-to-End Speech Processing Toolkit
[TensorFlow] Face Generation using Generative Adversarial Networks (GANs); Generated new images from MINST & CelebA dataset using batch normalization technique, D/G Loss = 0.5 - 1.8
A Full Stack project built on Ruby on Rails, JS, React/Redux.
[TensorFlow] Image Classification using Convolutional Neural Networks (CNNs); Classified images from the CIFAR-10 dataset using maxpool and dropout techniques, validation accuracy = 0.60
[TensorFlow] Language Translation using seq2seq RNNs; Translated new sentences from English to French using encoder/decoder techniques, validation accuracy = 0.96
LLM chatbot based on Retrieval Augmented Generation (RAG)
Deep Learning Foundation Nanodegree Program. Mini Project: sentiment-network
[Django] Social Platform Web Application using Django (Full Stack Developer)
[TensorFlow] Stock Prediction Application using Feedforward Neural Networks (FNNs); Predicted the daily S&P500 index price using TensorFlow with multiple input features, validation error ~= 1%
[Scikit-learn] Temperature Prediction Application using Machine Learning Algorithms; Predicted daily temperature using multiple Linear Regression models & MLP with Scikit-learn, score = 0.85
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
Practical tutorials and labs for TensorFlow used by Nvidia, FFN, CNN, RNN, Kaggle, AE
[TensorFlow] Generate TV Scripts using Recurrent Neural Networks (RNNs); Generated new Simpsons TV scripts using word embedding and LSTM techniques, cross-entropy loss = 0.33
USC Image Processing Term Project (2009): Improved the Multi-scale Error Diffusion (MED) Technique of Digital Halftoning using C (Image Processing); Improved MED runtime by 70%; implemented other algorithms: Direct Binarization, Dithering, and Error Diffusion
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.