lrnavin Goto Github PK

adaboost

AdaBoost and WeakLearner Implemetation

attentive-neural-process

A Pytorch Implementation of Attentive Neural Process

attentive-neural-processes

implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)

autocomments

Description: We want to create a deep Neural Network that can automatically generate comments for code snippets passed to it. The motivation behind this is that in software development and maintenance, developers spend around 59% of their time on program comprehension activities. Having comments that are generated automatically will hopefully cut this time down. In order to do this we will combine the recent paper Code2Vec: Learning Distributed Representations of Code by Alon et al. with the paper Deep Code Comment Generation in order to make a better performing model using the newer Code2Vec encoding that was not used in the Deep Code Comment Generation paper. Dataset: The dataset that we will use is the same dataset used by the Deep Code Comment Generation paper, this is a dataset of more than 500,000 code snippets including comments. This also gives us a baseline against which to compare. Papers: Deep Code: https://xin-xia.github.io/publication/icpc182.pdf Code2Vec: https://arxiv.org/abs/1803.09473

bayesianlearning

Coursera HSE Course

big_data

In this lab we will put the concepts that are central to Supercomputing with Big Data in some practical context. We will analyze a large open data set and identify a way of processing it efficiently using Apache Spark and the Ama- zon Web Services (AWS). The data set in question is the GDELT 2.0 Global Knowledge Graph (GKG), which indexes persons, organizations, companies, locations, themes, and even emotions from live news reports in print, broad- cast and internet sources all over the world. We will use this data to construct a histogram of the topics that are most popular on a given day, hopefully giving us some interesting insights into the most important themes in recent history.

conversation_quality

cyberdata_analytics

datasciencecoursera

datasharing

The Leek group guide to data sharing

dataviz-infoviz

Front End

deeplearning_project

Quarter-3, Deep Learning Project

delftds_hashcode_practice

ecorp_fairness_ml

Machine Learning Challenge from E-Corp. We are dealing with a two-class classificaiton problem that revolves around so-called fairness. Our objects are people.

furhatmimicry

Conversation AI project: Enable Furhat to mimic conversation partner's Head Pose and Gestures.

google-api-objectivec-client

Automatically exported from code.google.com/p/google-api-objectivec-client

googlehash

Practise for Google Hash

hiddenmarkovmodellearning

lrnavin.github.io

mnist_classifier

Patter Recognition - Analysis of Classifer in MNIST

multi_instance_learning

navinrajprabhu.github.io

neural-processes

This repository contains notebook implementations of the following Neural Process variants: Conditional Neural Processes (CNPs), Neural Processes (NPs), Attentive Neural Processes (ANPs).

nickjr.bundle

nlp_tensorflow

nmc_regularisation

Regularization & Sparsity in Nearest Mean Classifier

online_learning

Stock Market/Bitcoin Prediciton through Online Learning

openface

OpenFace – a state-of-the art tool intended for facial landmark detection, head pose estimation, facial action unit recognition, and eye-gaze estimation.

painters_by_numbers

In this project we have evaluated approaches to the challenge proposed on Kaggle named {Painter by Numbers}. The objective of this challenge is to distinguish whether two paintings were created by the same artist in the process of pairwise comparison. In a broad sense this could improve the identification of forgeries based on learned {artist style}. The dataset for the challenge is a collection of paintings from WikiArt.org {http://wikiart.org}. After analyzing approaches taken by other competitors, we have identified a gap that could be explored: creating a network that not only learns the style from artists included in the provided dataset, but also is able to give a correct verdict for an artist that are not included in the training data. This creates an additional layer of complexity as the network has to facilitate ability to {generalize to unseen artists}. To tackle the problem at hand, a neural network architecture called the siamese network was used.

reinforcement_learn

Machine Learning Assignment