26 skills found
facebookresearch / SvoiceWe provide a PyTorch implementation of the paper Voice Separation with an Unknown Number of Multiple Speakers In which, we present a new method for separating a mixed audio sequence, in which multiple voices speak simultaneously. The new method employs gated neural networks that are trained to separate the voices at multiple processing steps, while maintaining the speaker in each output channel fixed. A different model is trained for every number of possible speakers, and the model with the largest number of speakers is employed to select the actual number of speakers in a given sample. Our method greatly outperforms the current state of the art, which, as we show, is not competitive for more than two speakers.
alvinwan / Neural Backed Decision TreesMaking decision trees competitive with neural networks on CIFAR10, CIFAR100, TinyImagenet200, Imagenet
gangweix / CGI StereoA novel neural network architecture that can concurrently achieve real-time performance, competitive accuracy, and strong generalization ability.
ruvnet / Flow NexusFlow Nexus is the first competitive agentic platform built entirely on MCP. Deploy autonomous AI swarms, train neural networks, and compete in coding challenges while earning rUv credits. Transform agentic engineering mastery into lived experience through gamified cloud development where agents spawn agents and systems improve themselves
EnnaSachdeva / Recurrent Multiagent Deep Deterministic Policy Gradient With Difference RewardsDeep Reinforcement Learning (DRL) algorithms have been successfully applied to a range of challenging simulated continuous control single agent tasks. These methods have further been extended to multiagent domains in cooperative, competitive or mixed environments. This paper primarily focuses on multiagent cooperative settings which can be modeled for several real world problems such as coordination of autonomous vehicles and warehouse robots. However, these systems suffer from several challenges such as, structural credit assignment and partial observability. In this paper, we propose Recurrent Multiagent Deep Deterministic Policy Gradient (RMADDPG) algorithm which extends Multiagent Deep Determinisitic Policy Gradient algorithm - MADDPG \cite{lowe2017multi} by using a recurrent neural network for the actor policy. This helps to address partial observability by maintaining a sequence of past observations which networks learn to preserve in order to solve the POMDP. In addition, we use reward shaping through difference rewards to address structural credit assignment in a partially observed environment. We evaluate the performance of MADDPG and R-MADDPG with and without reward shaping in a Multiagent Particle Environment. We further show that reward shaped RMADDPG outperforms the baseline algorithm MADDPG in a partially observable environmental setting.
Zi-YuanYang / CO3NetCode of ”CO3Net: Coordinate-Aware Contrastive Competitive Neural Network for Palmprint Recognition“ (Accepted by IEEE TIM)
xuliangcs / CompnetSupplementary Materials for the 2021 IEEE SPL paper "CompNet: Competitive Neural Network for Palmprint Recognition Using Learnable Gabor Kernels"
Remtasya / Distributional Multi Agent Actor Critic Reinforcement Learning MADDPG Tennis EnvironmentThe state-of-the-art in multi-agent Reinforcement Learning is the MADDPG algorithm which utilises DDPG actor-critic neural networks where each agent uses centralized critic training but decentralized actor execution, and is capable of learning either cooperative or competitive environments. This is demonstrated on the Unity Tennis Environment.
iinaimaf / Hybridized Harris Hawk Whale Optimization AlgorithmUses Harris Hawk and Whale Nature Inspired Algorithm to Train the weights of Neural Network. An approach to adjust the parameters of NN connection weights using the hybrid of Harris Hawk Optimization and Whale Optimization algorithm was proposed. The results showed that the hybrid algorithm has been successfully applied to train neural networks. The results showed that there is no superiority of one algorithm over another, however, the results of the proposed algorithm are a competitive alternative to other P-Metaheuristic algorithms. Hybrid Harris Hawk with Whale optimization to train weights of the neural network was used to increase the efficiency of fraud detection and cancer datasets. Our method for anomaly detection is a supervised method based on classification. The performance of Harris Hawk with Whale is acceptable and has promising results that nominate it for other optimization applications such as scheduling.
mohammad-AJP / Neural Network Weight Improvement Using Optimization AlgorithmsGray Wolf Optimization (GWO), Imperialist Competitive Algorithm (ICA) and Particle Swarm Optimization (PSO) are used to improve the weights achieved by a Neural Network trained with Gradient Descent method
IBM / Distributed Evolutionary MlA tool for experimenting with evolutionary optimization methods for machine learning algorithms, by distributing the workload over a large number of compute nodes on the IBM Cloud. For now, it only includes an implementation of [Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning](https://arxiv.org/abs/1712.06567).
Rohithram / Self Organizing Maps Using KNNHigh Frequency Time series Anomaly Detection using Self Organizing Maps (SOM) which is based on Competitive Learning a variant of the Neural Networks using K Nearest Neighbors
asthanameghna / Relightable BRDF NeRFWe propose to tackle the multiview photometric stereo problem using an extension of Neural Radiance Fields (NeRFs), conditioned on light source direction. The geometric part of our neural representation predicts surface normal direction, allowing us to reason about local surface reflectance. The appearance part of our neural representation is decomposed into a neural bidirectional reflectance function (BRDF), learnt as part of the fitting process, and a shadow prediction network (conditioned on light source direction) allowing us to model the apparent BRDF. This balance of learnt components with inductive biases based on physical image formation models allows us to extrapolate far from the light source and viewer directions observed during training. We demonstrate our approach on a multiview photometric stereo benchmark and show that competitive performance can be obtained with the neural density representation of a NeRF.
kietnv / VireaderMachine Reading Comprehension has attracted significant interest in research on natural language understanding, and large-scale datasets and neural network-based methods have been developed for this task. However, most developments of resources and methods in machine reading comprehension have been investigated using two resource-rich languages, English and Chinese. This article proposes a system called ViReader for open-domain machine reading comprehension in Vietnamese by using Wikipedia as the textual knowledge source, where the answer to any particular question is a textual span derived directly from texts on Vietnamese Wikipedia. Our system combines a sentence retriever component, based on techniques of information retrieval to extract the relevant sentences, with a transfer learning-based answer extractor trained to predict answers based on Wikipedia texts. Experiments on multiple datasets for machine reading comprehension in Vietnamese and other languages demonstrate that (1) our ViReader system is highly competitive with prevalent machine learning-based systems, and (2) multi-task learning by using a combination consisting of the sentence retriever and answer extractor is an end-to-end reading comprehension system. The sentence retriever component of our proposed system retrieves the sentences that are most likely to provide the answer response to the given question. The transfer learning-based answer extractor then reads the document from which the sentences have been retrieved, predicts the answer, and returns it to the user. The ViReader system achieves new state-of-the-art performances, with values of 70.83% EM (exact match) and 89.54% F1, outperforming the BERT-based system by 11.55% and 9.54%, respectively. It also obtains state-of-the-art performance on UIT-ViNewsQA (another Vietnamese dataset consisting of online health-domain news) and BiPaR (a bilingual dataset on English and Chinese novel texts). Compared with the BERT-based system, our system achieves significant improvements (in terms of F1) with 7.65% for English and 6.13% for Chinese on the BiPaR dataset. Furthermore, we build a ViReader application programming interface that programmers can employ in Artificial Intelligence applications.
JonnyLewis / CompnetSupplementary Materials for the 2021 IEEE SPL paper "CompNet: Competitive Neural Network for Palmprint Recognition Using Learnable Gabor Kernels"
leobispo / SomSOM - Self organizing Map is a Swing application that implements the Self organizing map algorithm. Self-organizing map (SOM) is a type of artificial neural network that is trained using unsupervised learning to produce low-dimensional representation of the training samples while preserving the topological properties of the input space. Self-Organizing Map showing US Congress voting patterns visualized in Synapse Self-Organizing Map showing US Congress voting patterns visualized in Synapse This makes SOM useful for visualizing low-dimensional views of high-dimensional data, akin to multidimensional scaling. The model was first described as an artificial neural network by the Finnish professor Teuvo Kohonen, and is sometimes called a Kohonen map. Like most artificial neural networks, SOMs operate in two modes: training and mapping. Training builds the map using input examples. It is a competitive process, also called vector quantization. Mapping automatically classifies a new input vector.
shiluqiang / Competitive Neural NetworkCompetitive Neural Network for cluster
t-shinozaki / ConvcpCompetitive Learning for Convolutional Neural Networks
saunak1994 / CyNAPSEA Low-Power Neural Processing Engine for reconfigurable spiking competitive networks
selforgmap / Som CppSelf Organizing Map (SOM) is a type of Artificial Neural Network (ANN) that is trained using an unsupervised, competitive learning to produce a low dimensional, discretized representation (feature map) of higher dimensional data.
