March 30, 2022 Neural Network

CoNeRF: Controllable Neural Radiance Fields

This is the official implementation for “CoNeRF: Controllable Neural Radiance Fields” The codebase is based on HyperNeRF implemente in JAX, building on JaxNeRF. Setup The code can be run under any environment with Python 3.8 and above. (It may run with lower versions, but we have not tested it). We recommend using Miniconda and setting up an environment: conda create –name conerf python=3.8 Next, install the required packages: pip install -r requirements.txt Install the appropriate JAX distribution

March 25, 2022 Neural Network

Graph Neural Networks for User Identity Linkage

data/: contains the processed data. The dataset Douban-Weibo is provided by the PHD student Siyuan Chen. If you use the data, please cite the following paper. More details refer to INFUNE. @inproceedings{chen2020infune, title={A Novel Framework with Information Fusion and Neighborhood Enhancement for User Identity Linkage}, author={Chen, Siyuan and Wang, Jiahai and Du, Xin and Hu, Yanqing}, booktitle={24th European Conference on Artificial Intelligence (ECAI)}, pages={1754–1761}, year={2020} }

March 21, 2022 Neural Network

Neural Network to classify Road Signs based on their images

As research in the field of Self-Driving cars continues, one of the most important challenges faced by scientists and engineers is Computer Vision. Computer Vision allows these cars to develop an understanding of their environment by analyzing digital images. Therefore what we are going to be dealing with is the ability to recognize and distinguish between differetn road signs like for example the STOP signal, SPEED LIMIT signs, yield signs, etc. So, in this project, I have used Tensorflow to […]

March 1, 2022 Neural Network

A generic code base for neural network pruning, especially for pruning at initialization

This repository is meant to provide a generic code base for neural network pruning, especially for pruning at initialization (PaI). [Survey | Paper Collection] Step 1: Set up environment OS: Linux (Ubuntu 1404 and 1604 checked. It should be all right for most linux platforms. Windows and MacOS not checked.) python=3.6.9 (conda to manage environment is strongly suggested) All the dependant libraries are summarized in requirements_pt1.9.txt (PyTorch 1.9 is used). Simply install them by pip install -r requirements_pt1.9.txt. CUDA and […]

February 1, 2022 Neural Network

Discovering Invariant Rationales for Graph Neural Networks

“Discovering Invariant Rationales for Graph Neural Networks” (ICLR 2022) aims to train intrinsic interpretable Graph Neural Networks that are generalizable to out-of-distribution datasets. The core of this work lies in the construction of environments, i.e., interventional distributions, and thus discovering the causal features for rationalization. Installation Main packages: PyTorch >= 1.5.0, Pytorch Geometric >= 1.7.0, OGB >= 1.3.0. See requirements.txt for other packages. Data download Spurious-Motif: this dataset can be generated via spmotif_gen/spmotif.ipynb. Graph-SST2: this dataset can be downloaded here. […]

January 28, 2022 Neural Network

Improving Neural Cross-lingual Abstractive Summarization via Employing Optimal Transport Distance for Knowledge Distillation

This repository contains the implementation of the paper Improving Neural Cross-lingual Abstractive Summarization via Employing Optimal Transport Distance for Knowledge Distillation. Thong Nguyen, Luu Anh Tuan (AAAI 2022) In this paper, we propose a novel Knowledge Distillation framework to tackle Neural Cross-Lingual Summarization for morphologically or structurally distant languages. In our framework, we propose a novel Knowledge Distillationframework to tackle Neural Cross-Lingual Summarization for morphologically or structurally distant languages. Extensive experiments in both high and low-resourced settings on multiple Cross-Lingual […]

January 22, 2022 Neural Network

Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently

This repository is the official implementation for the following paper Analytic-LISTA networks proposed in the following paper: “Peek-a-Boo: What (More) is Disguised in a Randomly Weighted Neural Network, and How to Find It Efficiently” by Xiaohan Chen, Jason Zhang and Zhangyang Wang from the VITA Research Group. The code implements the Peek-a-Boo (PaB) algorithm for various convolutional networks and is tested in Linux environment with Python: 3.7.2, PyTorch 1.7.0+. Getting Started Dependency Prerequisites Python 3.7+ PyTorch 1.7.0+ tqdm Data Preparation […]

January 17, 2022 Neural Network

Evolving neural network parameters in JAX

This repository holds code displaying techniques for applying evolutionary network training strategies in JAX. Each script trains a network to solve the same problem: given a sequence of regularly-spaced values on a sine wave, predict the next value. The problem is trivial – the interesting part is intended to be the way in which this is accomplished, by updating network parameters directly and without gradient calculations, in parallel across devices. A lengthy tutorial is included, explaining the ideas and rationale. […]

January 16, 2022 Neural Network

From Perceptron model to Deep Neural Network from scratch in Python

Aim of this Repository: From Perceptron model to Deep Neural Network (from scratch) in Python. ** Currently working on a basic Neural network model. Reference for the Perceptron model: https://www.youtube.com/watch?v=ntKn5TPHHAk&list=PLRqwX-V7Uu6aCibgK1PTWWu9by6XFdCfh&index=3&t=217s GitHub View Github

January 9, 2022 Neural Network

A simple Neural Network from scratch in Python using the Pymathrix library

A Simple Neural Network from scratch in Python using the Pymathrix library.Check the Pymathrix documentation. Usage Import the Pymathrix library into your python code: >> inputs = px.matrix(1, 3) >>> inputs.assign([1, 1, -1])” readability=”10″> >>> inputs = px.matrix(1, 3) >>> inputs.assign([1, 1, -1]) Create the neural network object:

1 2 3 … 6 »