mapleyustat

btas

block-sparse tensor library and blas interfaces on blitz++

Fast-Detection-of-Overlapping-Communities-via-Online-Tensor-Methods

We present a fast tensor-based approach for detecting hidden overlapping communities under the Mixed Membership Stochastic Blockmodel (MMSB). We present two implementations, viz., a GPU-based implementation which exploits the parallelism of SIMD architectures and a CPU-based implementation for larger datasets, wherein the GPU memory does not suffice.

learning-wordnet

Learning wordnet using tensor neural network

libgpuarray

Library to manipulate tensors on the GPU.

multid

MultiD is n-dimensional nonlinear vector analysis---which includes n-dimensional linear algebra. The analysis takes place in n-dimensional linear spaces, but the maps between the spaces are, in general, nonlinear. Inside these spaces are geometric objects (points, arrows, curves, surfaces---to be implemented, etc.). The idea is to create a Scene in n-dimensions and have several "projections" (not necessarily linear) onto 2- and 3-dimensional spaces.

neuraltalk

NeuralTalk is a Python+numpy project for learning Multimodal Recurrent Neural Networks that describe images with sentences.

NSPSeg

N Shortest Path Chinese Words Segmetation in C++ Ｎ最短路径分词

quantum_walk_neural_network

This is an algorithm for quantum walk neural networks on a star-shaped graph. The quantum walker learns a transition matrix of the graph through the algorithm.

TTr1SVD

Tensor Train Rank-1 decomposition

xsegment

基于统计分词，汉字转拼音，句子情感

mapleyustat/Quantum-Walks-Time-Dependent-Hamiltonians

In this thesis we study the properties of quantum walks with time dependent Hamiltonians, focusing in particular on the application to the quantum search problem on graphs. We study the search, localization and give a measure of robustness.

mapleyustat/Adiabatic-Quantum-Walk

Adiabatic quantum search algorithm on graph

mapleyustat/AtmosDensityModeling

Knowledge of accurate thermospheric density is important for accurate satellite orbital path predictions. However, previous best in class empirical models utilize linear mapping techniques to represent a highly non linear system. Here, I explore the application of Deep Feedforward and Long Short Term Memory Neural Networks in density prediction to better map complexities in data.

mapleyustat/BinaryBrain

Binary Neural Network for FPGA (LUT-Network)

mapleyustat/COVID19-AI-Quantum-Tensorflow

Open-source Artificial Intelligence & Quantum Technologies research and development. Quantum/AI algorithms built with Tensorflow Quantum technologies, aimed at fighting and understanding COVID-19.

mapleyustat/covid19_spell

Analyses performed by the Spatial Epidemiology Lab (SpELL - ULB) on COVID-19 data

mapleyustat/CRUSOE

CRUSOE: A Toolset for Cyber Situational Awareness and Decision Support in Incident Handling Inspired by the OODA Loop

mapleyustat/deepmind-research

This repository contains implementations and illustrative code to accompany DeepMind publications

mapleyustat/deepxde

A library for scientific machine learning and physics-informed learning

mapleyustat/Grassmann.jl

⟨Leibniz-Grassmann-Clifford⟩ differential geometric algebra / multivector simplicial complex

mapleyustat/hsim

Fast Hamiltonian Simulation

mapleyustat/MA_visualization

Processing and visualization of datasets used for middle-atmosphere research

mapleyustat/MCRN-DA

This project involves developing reduced physical and data models and algorithms for data assimilation. The goal of the project is to address computational challenges in data assimilation of dimensionality and non-Gaussian behavior for model problems and relevant small to medium scale problems. This includes a models from many different possible areas: atmosphere, ocean, combined atmosphere/ocean, ice sheet, glacier, hurricane, ENSO, polar vortex, ecological models, etc.. The basic idea is to create computational conceptual models, both physical and data models, and combine these with standard data assimilation techniques and new techniques developed to take advantage of the structure of these conceptual models. Among the data assimilation techniques to be considered are projected particle filters. Focus is on application to problems with bimodal or multimodal behavior which ties in with work on tipping points. Another emphasis is on applying these techniques to higher dimensional problems to create lower dimensional computational conceptual models. The project involves employing, developing, and applying projected data assimilation techniques, in particular projected particle filters, using the framework developed in (Maclean, VV 2019), while focusing on the use of different state space and observation space projections for increasingly high dimensional models.

mapleyustat/MSSL

Research internship at MSSL Space Plasma group, using Machine Learning to predict space weather events

mapleyustat/neural-backed-decision-trees

Making decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet

mapleyustat/NeuralQuantum.jl

Neural-Network representation of Quantum Systems

mapleyustat/neuroptica

Flexible simulation package for optical neural networks

mapleyustat/ooda-loop

OODA loop demo

mapleyustat/ooda_flow_diagram

OODA Flow Diagram supports your OODA Loop projects.

mapleyustat/QuAlgorithmZoo.jl

A curated implementation of quantum algorithms with Yao.jl

mapleyustat/quantum_walk

Spatial search by quantum walk

mapleyustat/QuantumAlgebra.jl

Quantum operator algebra in Julia

mapleyustat/qwgc

Quantum Walk Graph Classifier

mapleyustat/sabcom

The Spatial Agent-Based Covid Model (SABCom)

mapleyustat/sandboxie

The Sandboxie application

mapleyustat/SetReplace

Wolfram Language Package for exploring Set Substitution Systems (Wolfram Models)

mapleyustat/Space-Weather-Prediction

My attempt to develop and use Machine Learning Models to Forecasting Time Series of Space Weather Phenomena

mapleyustat/space-weather-prediction-1

mapleyustat/standard-atmosphere

Standard atmosphere gas properties. Support for n-dim inputs, non-standard atmospheres, units, etc.

mapleyustat/Visualising-the-DFN-Dataset

The Desert Fireball Network (DFN) has a sizeable dataset on the orbits of small bodies in our solar system. As a summer scholarship with the Curtin HIVE in 2019-2020, a Unity project was created for the DFN that visualised this dataset in an interactive dynamic environment. The scripts in this repository are Unity scripts.