ili i. 's Projects
Algorithm competition and practice codes.
A free Jekyll theme
The Berkeley Document Summarizer is a learning-based, single-document summarization system that extracts source document content, exploits syntactic information to compress it, and uses coreference constraints to ensure clarity.
A brazen two-column theme for Jekyll.
The original code from the DeepMind article + my tweaks
Lightweight browser-based display server
Efficient Hyperparameter Optimization of Deep Learning Algorithms Using Deterministic RBF Surrogates
LabNotebook is a tool that allows you to flexibly monitor, record, save, and query all your machine learning experiments.
A tiny logging module for Lua
A PDTB-Styled End-to-End Discourse Parser
Sequence-to-sequence model with LSTM encoder/decoders and attention
The Software Development Guidelines I developed while working as a team lead at Neuri.
StackOverflow parsing and API usage to show some users statistics.
Torch C data structures
Torch interface to HDF5 library
This library provides utilities for creating and manipulating RNNs to model sequential data.
Automatically collect and visualize usage statistics in Ubuntu/OSX environments.
Accompanying code for "A Simple Loss Function for Improving the Convergence and Accuracy of Visual Question Answering Models" CVPR 2017 VQA workshop paper.
Visual Question Answering in Pytorch
Scorer for PDTB relations