26 papers · ranked by Valyu relevance
Sebastián Basterrech, Gerardo Rubino
Random Neural Networks (RNNs) are a class of Neural Networks (NNs) that can also be seen as a specific type of queuing network. They have been successfully used in several domains during the last 25 years, as queuing networks to analyze the performance of resource sharing in many engineering areas, as learning tools…
Sebastián Basterrech, Gerardo Rubino
—In the last decade, a new computational paradigm was introduced in the field of Machine Learning, under the name of Reservoir Computing (RC). RC models are neural networks which a recurrent part (the reservoir) that does not participate in the learning process, and the rest of the system where no recurrence (no neural…
Yonghua Yin
The random neural network (RNN) is a mathematical model for an "integrate and fire" spiking network that closely resembles the stochastic behaviour of neurons in mammalian brains. Since its proposal in 1989, there have been numerous investigations into the RNN's applications and learning algorithms. Deep learning (DL)…
Saining Xie, Alexander Kirillov, Ross Girshick, Kaiming He
Neural networks for image recognition have evolved through extensive manual design from simple chain-like models to structures with multiple wiring paths. The success of ResNets [11] and DenseNets [16] is due in large part to their innovative wiring plans. Now, neural architecture search (NAS) studies are exploring the…
Kun Lang, Mingyuan Zhang, Yongbo Yuan, Jesus Malo
An effective forecasting model for short-term load plays a significant role in promoting the management efficiency of an electric power system. This paper proposes a new forecasting model based on the improved neural networks with random weights (INNRW). The key is to introduce a weighting technique to the inputs of…
Jihang Wang, Dongcheng Zhao, Chengcheng Du, Xiang He + 2 more
'Yi Zeng'] Title: Summary Spiking neural networks (SNNs) offer a biologically inspired alternative to artificial neural networks (ANNs) by mimicking neuronal information transmission mechanisms. However, similar to ANNs, SNNs remain susceptible to adversarial examples, raising concerns about their robustness in…
Zihan Dai, Huanfei Ma
The spiking neural network, known as the third generation neural network, is an important network paradigm. Due to its mode of information propagation that follows biological rationality, the spiking neural network has strong energy efficiency and has advantages in complex high-energy application scenarios. However…
Fenglei Fan, Ge Wang
— Inspired by the fact that the neural network, as the mainstream method for machine learning, has brought successes in many application areas, here we propose to use this approach for decoding hidden correlation among pseudo-random data and predicting events accordingly. With a simple neural network structure and a…
Amr Farahat, Martin Vinck
Convolutional neural networks (CNNs) were inspired by the organization of the primate visual system, and in turn have become effective models of the visual cortex, allowing for accurate predictions of neural stimulus responses. While training CNNs on brain-relevant object-recognition tasks may be an important…
Yu Terada, Taro Toyoizumi
Cortical neurons exhibit highly variable responses over trials and time. Theoretical works posit that this variability arises potentially from chaotic network dynamics of recurrently connected neurons. Here we demonstrate that chaotic neural dynamics, formed through synaptic learning, allow networks to perform sensory…
Claudio Gallicchio, Simone Scardapane
Randomized Neural Networks explore the behavior of neural systems where the majority of connections are fixed, either in a stochastic or a deterministic fashion. Typical examples of such systems consist of multi-layered neural network architectures where the connections to the hidden layer(s) are left untrained after…
Thomas Lynn, Julio Ottino, Richard Lueptow, Paul Umbanhowar
Cut-and-shuffle mixing is an instructive candidate system with which to assess the potential of machine learning (ML) as an approach to solve difficult mixing problems. We focus on a specific subset of cut-and-shuffle systems, the one-dimensional interval exchange transform. This class of mixing operations is well…
Lars Buesing, Johannes Bill, Bernhard Nessler, Wolfgang Maass + 1 more
'Olaf Sporns'] The organization of computations in networks of spiking neurons in the brain is still largely unknown, in particular in view of the inherently stochastic features of their firing activity and the experimentally observed trial-to-trial variability of neural systems in the brain. In principle there exists…
Christian Lee, Zheng Zhang, Skirmantas Janušonis
Random dropout has become a standard regularization technique in artificial neural networks (ANNs), but it is currently unknown whether an analogous mechanism exists in biological neural networks (BioNNs). If it does, its structure is likely to be optimized by hundreds of millions of years of evolution, which may…
Miquel L. Alomar, Vincent Canals, Nicolas Perez-Mora, Víctor Martínez-Moll + 1 more
'Víctor Martínez-Moll' 'Josep L. Rosselló'] Hardware implementation of artificial neural networks (ANNs) allows exploiting the inherent parallelism of these systems. Nevertheless, they require a large amount of resources in terms of area and power dissipation. Recently, Reservoir Computing (RC) has arisen as a…
Christian Lee, Zheng Zhang, Skirmantas Janušonis
Random dropout has become a standard regularization technique in artificial neural networks (ANNs), but it is currently unknown whether an analogous mechanism exists in biological neural networks (BioNNs). If it does, its structure is likely to be optimized by hundreds of millions of years of evolution, which may…
Hesham Mostafa, Vishwajith Ramesh, Gert Cauwenberghs
Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from higher layers. Learning using delayed and non-local errors makes it hard to reconcile…
David G. Clark, Blake Bordelon, Jacob A. Zavatone-Veth, Cengiz Pehlevan
Across many brain areas, neurons produce heterogeneous, seemingly disordered responses. Yet the circuits these neurons comprise cannot be purely random; they must possess some structure to generate representations and computations underlying behavior. How much structure is present in recurrent connectivity relative to…
Xu Pan, Ruben Coen-Cagli, Odelia Schwartz
Convolutional neural networks (CNNs) have been used to model the biological visual system. Compared to other models, CNNs can better capture neural responses to natural stimuli. However, previous successes are limited to modeling mean responses; while another fundamental aspect of cortical activity, namely response…
Jonathan C Kao
Recurrent neural networks (RNNs) are increasingly being used to model complex cognitive and motor tasks performed by behaving animals. Here, RNNs are trained to reproduce animal behavior while also recapitulating key statistics of empirically recorded neural activity. In this manner, the RNN can be viewed as an in…
Authors not listed
Real-world datasets in chemical engineering and bioengineering processes--such as those from catalytic reactors, multiphase flows, polymerization reactors, bioreactors, and clinical trials--can often be unlabelled or disorganized, rendering the training of existing supervised learning models ineffective at learning the…
Sanjar Adilov
Generative neural networks have shown promising results in de novo drug design. Recent studies suggest that one of the efficient ways to produce novel molecules matching target properties is to model SMILES sequences using deep learning in a way similar to language modeling in natural language processing. In this…
James Swift, Matthew Arran Turner, James Christopher Reynolds
A rapid headspace analysis method for the authenticity testing of whiskies of different brands and years was developed for a low cost, deployable atmospheric pressure ionisation mass spectrometer, which required minimal sample preparation. Principal component analysis was applied to the time-averaged mass spectra, the…
Authors not listed
Transferable neural network potentials (NNP) are undergoing rapid development. Many practical applications of NNPs focus on single molecules; e.g., using NNPs as a fast replacement for quantum chemical methods for dihedral angle scans in force field development. Similarly, the reference data on which most transferable…
Sofía Lawrie, Rubén Moreno-Bote, Matthieu Gilson
In biological neuronal networks, information representation and processing are achieved through plasticity learning rules that have been empirically characterized as sensitive to second and higher-order statistics in spike trains. However, most models in both computational neuroscience and machine learning aim to…
Authors not listed
Finding microkinetic parameters for heterogeneously catalyzed processes with conventional methods is a challenging task. Recently, the use of artificial neural networks has been described as a promising and flexible tool for kinetic parameter estimation. In this work, an extension to the methodology of chemical reaction…