Empirical Study of Recent Face Alignment Methods

Code for our ICAR 2019 paper "ANDA: A Novel Data Augmentation Technique Applied to Salient Object Detection"

An implementation for attention model in Keras for sequence to sequence model.

Notes and experiments to understand deep learning concepts

I have tried some of the machine learning and deep learning algorithm for IDS 2017 dataset. The link for the dataset is here: http://www.unb.ca/cic/datasets/ids-2017.html. By keeping Monday as the training set and rest of the csv files as testing set, I tried one class SVM and deep CNN model to check how it works. Here the Monday dataset contains only normal data and rest of the days contains both normal and attacked data. Also, from the same university (UNB) for the Tor and Non Tor dataset, I tried K-means clustering and Stacked LSTM models in order to check the classification of multiple labels.

J583 Advanced Interactive Media

Association Rule Mining from Spatial Data for Crime Analysis

Sentiment Analysis with LSTMs in Tensorflow

deeplearn.js meets p5

All the notebooks for the analysis of Emotional Arcs within the Project Gutenberg corpus, see "The emotional arcs of stories are dominated by six basic shapes"

Home of the Semi-Analytic Galaxy Evolution (SAGE) galaxy formation model

Utility to generate plots with categorical variables using Altair.

Deployment template for Azure WebApp, CNTK, Python 3 (x64) and sample model

Bayesian methods in deep learning Summer School

Entry for Grab's AI for S.E.A. challenge

The fastest way for developers and managers to gain practical ML knowledge and to apply it to their own projects.

Merge and Acquisitions Prediction based on M&A information from Crunchbase.

Keras implementation of the multi-channel cascaded architecture introduced in the paper "Brain Tumor Segmentation with Deep Neural Networks"