Development of IP code based on VIPs and AADM

Overview

Sparse Implicit Processes

In this repository we include the two different versions of the SIP code developed for the article Sparse Implicit Processes for Approximate Inference.

Structure of the code

We have two setups for the model: one that makes use of BNNs to model the implicit prior distribution, and another that uses Neural Samplers to do so. The BNN-based can be found in VIIP-BNN_prior, and the NS-based on VIIP-NS_prior. For each of them, the structure of the code goes as follows:

  • SIP_bnn.py or SIP_ns.py: Main body of the code. Includes calls to other functions to make the calculations needed in the model.

  • aux_functions.py: Create auxiliary functions that estimate moments from given samples of functions evaluated at selected points (mean, deviation and covariance between two collections of samples).

  • prior_BNN.py or prior_neural_sampler.py: Creates the prior samples of functions. Weight parameters (means and variances) are created and imported into the main NN. This, given an input (x), outputs f_S(x) according to the prior, which can be parametrized either as a BNN or a NS, depending on the selected folder.

  • discriminators.py: Creates and computes the output of both discriminators now needed in the procedure (since now both the approximating distribution and the prior are defined implicitly). There is a discriminator for each distribution samples (prior p(ยท) and approximating distribution q(ยท)).

  • posterior_neural_sampler.py: Creates the NS that will output samples from the approximating distribution. Using gaussian noise as input and processing it through a NN, samples of (u) are given (with shape defined through the calling of the function). The posterior is the same for both models implemented.

The rest of the python codes present in each folder serve to control the random variables, as well as their precision.

To run the code, do: python SIP_main.py [split] [alpha value] [n_layers (1 or 2)] [dataset as .txt]

The rest of the codes included here, and additional folders that may appear are just auxiliary and extra material that aid to develop the main code, on which it is based on. We have also included a .yml file to replicate the conda environment we have employed to conduct the experiments.

codebase for "A Theory of the Inductive Bias and Generalization of Kernel Regression and Wide Neural Networks"

Eigenlearning This repo contains code for replicating the experiments of the paper A Theory of the Inductive Bias and Generalization of Kernel Regress

Jamie Simon 45 Dec 02, 2022
Distributing reference energies for SMIRNOFF implementations

Warning: This code is currently experimental and under active development. Is it not yet suitable for distribution or use as reference implementation.

Open Force Field Initiative 1 Dec 07, 2021
Pytorch Implementation of paper "Noisy Natural Gradient as Variational Inference"

Noisy Natural Gradient as Variational Inference PyTorch implementation of Noisy Natural Gradient as Variational Inference. Requirements Python 3 Pytor

Tony JiHyun Kim 119 Dec 02, 2022
Implementation of Neural Distance Embeddings for Biological Sequences (NeuroSEED) in PyTorch

Neural Distance Embeddings for Biological Sequences Official implementation of Neural Distance Embeddings for Biological Sequences (NeuroSEED) in PyTo

Gabriele Corso 56 Dec 23, 2022
World Models with TensorFlow 2

World Models This repo reproduces the original implementation of World Models. This implementation uses TensorFlow 2.2. Docker The easiest way to hand

Zac Wellmer 234 Nov 30, 2022
Code for our CVPR 2022 Paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection"

GEN-VLKT Code for our CVPR 2022 paper "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection". Contributed by Yue Lia

Yue Liao 47 Dec 04, 2022
๐Ÿ›ฐ๏ธ Awesome Satellite Imagery Datasets

Awesome Satellite Imagery Datasets List of aerial and satellite imagery datasets with annotations for computer vision and deep learning. Newest datase

Christoph Rieke 3k Jan 03, 2023
An interpreter for RASP as described in the ICML 2021 paper "Thinking Like Transformers"

RASP Setup Mac or Linux Run ./setup.sh . It will create a python3 virtual environment and install the dependencies for RASP. It will also try to insta

141 Jan 03, 2023
Pytorch implementation of Nueral Style transfer

Nueral Style Transfer Pytorch implementation of Nueral style transfer algorithm , it is used to apply artistic styles to content images . Content is t

Abhinav 9 Oct 15, 2022
[ICCV'21] UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction

UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction Project Page | Paper | Supplementary | Video This reposit

331 Dec 28, 2022
Architecture Patterns with Python (TDD, DDD, EDM)

architecture-traning Architecture Patterns with Python (TDD, DDD, EDM) Chapter 5. ๋†’์€ ๊ธฐ์–ด๋น„์™€ ๋‚ฎ์€ ๊ธฐ์–ด๋น„์˜ TDD 5.2 ๋„๋ฉ”์ธ ๊ณ„์ธต ํ…Œ์ŠคํŠธ๋ฅผ ์„œ๋น„์Šค ๊ณ„์ธต์œผ๋กœ ์˜ฎ๊ฒจ์•ผ ํ•˜๋Š”๊ฐ€? ๋„๋ฉ”์ธ ๊ณ„์ธต ํ…Œ์ŠคํŠธ def

minsung sim 2 Mar 04, 2022
PyTorch implementation of our Adam-NSCL algorithm from our CVPR2021 (oral) paper "Training Networks in Null Space for Continual Learning"

Adam-NSCL This is a PyTorch implementation of Adam-NSCL algorithm for continual learning from our CVPR2021 (oral) paper: Title: Training Networks in N

Shipeng Wang 34 Dec 21, 2022
code for paper -- "Seamless Satellite-image Synthesis"

Seamless Satellite-image Synthesis by Jialin Zhu and Tom Kelly. Project site. The code of our models borrows heavily from the BicycleGAN repository an

Light 14 Apr 05, 2022
Iris prediction model is used to classify iris species created julia's DecisionTree, DataFrames, JLD2, PlotlyJS and Statistics packages.

Iris Species Predictor Iris prediction is used to classify iris species using their sepal length, sepal width, petal length and petal width created us

Siva Prakash 2 Jan 06, 2022
Custom TensorFlow2 implementations of forward and backward computation of soft-DTW algorithm in batch mode.

Batch Soft-DTW(Dynamic Time Warping) in TensorFlow2 including forward and backward computation Custom TensorFlow2 implementations of forward and backw

19 Aug 30, 2022
PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021.

GCResNet PyTorch implementation of Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution, IJCNN 2021. The code will

11 May 19, 2022
gACSON software for visualization, processing and analysis of three-dimensional electron microscopy images

gACSON gACSON software is to visualize, segment, and analyze the morphology of neurons in three-dimensional electron microscopy images. If you use any

Andrea Behanova 2 May 31, 2022
A repository for benchmarking neural vocoders by their quality and speed.

License The majority of VocBench is licensed under CC-BY-NC, however portions of the project are available under separate license terms: Wavenet, Para

Meta Research 177 Dec 12, 2022
Neuralnetwork - Basic Multilayer Perceptron Neural Network for deep learning

Neural Network Just a basic Neural Network module Usage Example Importing Module

andreecy 0 Nov 01, 2022