gaudelbijay Goto Github PK

followers: 13.0 following: 22.0 repos: 21.0 gists: 0.0

Name: Bijay Gaudel

Type: User

Bio: I like to train robots until symbiosis!

Twitter: bijaygaudelQ

Location: New Jersey

👋 Hi, I’m @gaudelbijay
👀 I’m interested in Machine Learning, Deep Learning, Computer Vision, Control System, Reinforcement Learning and Robotics
💞️ I’m looking to collaborate on Vision Based Control System for UAV
📫 How to reach me: [email protected]

Bijay Gaudel's Projects

autoencoders

Pytorch Implementation of different types of AutoEncoders

deepwalk

DeepWalk is network embedding technique proposed for learning the representations of nodes in a network, which is able to preserve the neighborhood structure of the nodes within a short random walk.

diffusion-defender

A diffusion-based denoising approach to mitigate online adversarial image attacks and an FFT-based detector

gan

Implementation of different types of GAN in pytorch

Line is a graph embedding technique, suitable for arbitrary types of information networks: undirected, directed, and/or weighted. The method optimizes a carefully designed objective function that preserves both the local and global network structures.

graphsagelite

A general framework that leverages node feature information (e.g., text attributes) to efficiently generate node embeddings for previously unseen data. Instead of training individual embeddings for each node, GraphSAGE learn a function that generates embeddings by sampling and aggregating features from a node’s local neighborhood. Here, the implementation of GraphSAGE is based on transductive training

graphsat

Graph sampling and attention

landinggeardetection-yolov4

landing gear detection training using YOLOV4.

nepaliautocompleteandlm

NepaliAutoCompleteML is a deep learning framework (using Pytorch) for suggesting relevant words during writing. We used Recurrent Neural Network with layer GRU or LSTM, and KL divergence as loss function to train our model.

node2vec

Node2Vec is an effective graph embedding technique which learns a mapping of nodes to a low dimensional space of features that maximizes the likelihood of preserving network neighborhoods of nodes.

sdne

Structural Deep Network Embedding (SDNE) is a semi-supervised deep model for graph embedding. Which has multiple layers of non-linear functions, thereby being able to capture the highly non-linear network structure.

sensor-api

Simple Flask API and Flutter App to track sensors data

simple_nn_visualizer

Simple neural network visualiser from coursera project

snnl-loss

Soft Nearest Neighbor loss from paper (https://arxiv.org/pdf/1902.01889.pdf) Implemented on tf 2.x

struc2vec

Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been adressed with representation learning techniques. Node2vec is a flexible framework for learning latent representation for the structural identity of nodes. Struc2vec uses a hierarchy to measure node similarity at different scales, and constructs a multilayer graph to encode structural similarities and generate structural context for nodes.

walks

Here I have coded the random_walk and biased random walk on the graph.

workshop2021

Basic of Deep Learning, Neural Networks, TensorFlow, and Machine Vision

gaudelbijay Goto Github PK

Bijay Gaudel's Projects

Recommend Projects

Recommend Topics

Recommend Org