88
88

Jun 29, 2018
06/18

by
Naman Agarwal; Zeyuan Allen-Zhu; Brian Bullins; Elad Hazan; Tengyu Ma

texts

######
eye 88

######
favorite 0

######
comment 0

We design a non-convex second-order optimization algorithm that is guaranteed to return an approximate local minimum in time which scales linearly in the underlying dimension and the number of training examples. The time complexity of our algorithm to find an approximate local minimum is even faster than that of gradient descent to find a critical point. Our algorithm applies to a general class of optimization problems including training a neural network and other non-convex objectives arising...

Topics: Data Structures and Algorithms, Machine Learning, Mathematics, Optimization and Control,...

Source: http://arxiv.org/abs/1611.01146

34
34

Jun 27, 2018
06/18

by
Dhagash Mehta; Crina Grosan

texts

######
eye 34

######
favorite 0

######
comment 0

Function optimization and finding simultaneous solutions of a system of nonlinear equations (SNE) are two closely related and important optimization problems. However, unlike in the case of function optimization in which one is required to find the global minimum and sometimes local minima, a database of challenging SNEs where one is required to find stationary points (extrama and saddle points) is not readily available. In this article, we initiate building such a database of important SNE...

Topics: Mathematical Software, Neural and Evolutionary Computing, Numerical Analysis, Optimization and...

Source: http://arxiv.org/abs/1504.02366

11
11

Jun 28, 2018
06/18

by
Nimrod Shaham; Yoram Burak

texts

######
eye 11

######
favorite 0

######
comment 0

It has been proposed that neural noise in the cortex arises from chaotic dynamics in the balanced state: in this model of cortical dynamics, the excitatory and inhibitory inputs to each neuron approximately cancel, and activity is driven by fluctuations of the synaptic inputs around their mean. It remains unclear whether neural networks in the balanced state can perform tasks that are highly sensitive to noise, such as storage of continuous parameters in working memory, while also accounting...

Topics: Quantitative Biology, Neurons and Cognition, Condensed Matter, Disordered Systems and Neural...

Source: http://arxiv.org/abs/1508.06944

27
27

Jun 30, 2018
06/18

by
Jonathan Long; Ning Zhang; Trevor Darrell

texts

######
eye 27

######
favorite 0

######
comment 0

Convolutional neural nets (convnets) trained from massive labeled datasets have substantially improved the state-of-the-art in image classification and object detection. However, visual understanding requires establishing correspondence on a finer level than object category. Given their large pooling regions and training from whole-image labels, it is not clear that convnets derive their success from an accurate correspondence model which could be used for precise localization. In this paper,...

Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...

Source: http://arxiv.org/abs/1411.1091

16
16

Jun 28, 2018
06/18

by
E. Romero; F. Mazzanti; J. Delgado

texts

######
eye 16

######
favorite 0

######
comment 0

Restricted Boltzmann Machines (RBMs) are general unsupervised learning devices to ascertain generative models of data distributions. RBMs are often trained using the Contrastive Divergence learning algorithm (CD), an approximation to the gradient of the data log-likelihood. A simple reconstruction error is often used as a stopping criterion for CD, although several authors \cite{schulz-et-al-Convergence-Contrastive-Divergence-2010-NIPSw,...

Topics: Computing Research Repository, Learning, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1507.06803

44
44

Jun 25, 2018
06/18

by
Chao Dong; Chen Change Loy; Kaiming He; Xiaoou Tang

texts

######
eye 44

######
favorite 0

######
comment 0

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural network (CNN) that takes the low-resolution image as the input and outputs the high-resolution one. We further show that traditional sparse-coding-based SR methods can also be viewed as a deep convolutional network. But unlike traditional methods that handle each component...

Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Neural and Evolutionary...

Source: http://arxiv.org/abs/1501.00092

10
10.0

Jun 27, 2018
06/18

by
Taichi Kiwaki

texts

######
eye 10

######
favorite 0

######
comment 0

We present a layered Boltzmann machine (BM) that can better exploit the advantages of a distributed representation. It is widely believed that deep BMs (DBMs) have far greater representational power than its shallow counterpart, restricted Boltzmann machines (RBMs). However, this expectation on the supremacy of DBMs over RBMs has not ever been validated in a theoretical fashion. In this paper, we provide both theoretical and empirical evidences that the representational power of DBMs can be...

Topics: Statistics, Computing Research Repository, Learning, Machine Learning, Neural and Evolutionary...

Source: http://arxiv.org/abs/1505.02462

14
14

Jun 27, 2018
06/18

by
Balakrishnan Varadarajan; George Toderici; Sudheendra Vijayanarasimhan; Apostol Natsev

texts

######
eye 14

######
favorite 0

######
comment 0

Video classification has advanced tremendously over the recent years. A large part of the improvements in video classification had to do with the work done by the image classification community and the use of deep convolutional networks (CNNs) which produce competitive results with hand- crafted motion features. These networks were adapted to use video frames in various ways and have yielded state of the art classification results. We present two methods that build on this work, and scale it up...

Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Multimedia, Neural and...

Source: http://arxiv.org/abs/1505.06250

12
12

Jun 27, 2018
06/18

by
Pulkit Agrawal; Joao Carreira; Jitendra Malik

texts

######
eye 12

######
favorite 0

######
comment 0

The dominant paradigm for feature learning in computer vision relies on training neural networks for the task of object recognition using millions of hand labelled images. Is it possible to learn useful features for a diverse set of visual tasks using any other form of supervision? In biology, living organisms developed the ability of visual perception for the purpose of moving and acting in the world. Drawing inspiration from this observation, in this work we investigate if the awareness of...

Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Robotics, Neural and...

Source: http://arxiv.org/abs/1505.01596

16
16

Jun 28, 2018
06/18

by
Bruno U. Pedroni; Srinjoy Das; John V. Arthur; Paul A. Merolla; Bryan L. Jackson; Dharmendra S. Modha; Kenneth Kreutz-Delgado; Gert Cauwenberghs

texts

######
eye 16

######
favorite 0

######
comment 0

Stochastic neural networks such as Restricted Boltzmann Machines (RBMs) have been successfully used in applications ranging from speech recognition to image classification. Inference and learning in these algorithms use a Markov Chain Monte Carlo procedure called Gibbs sampling, where a logistic function forms the kernel of this sampler. On the other side of the spectrum, neuromorphic systems have shown great promise for low-power and parallelized cognitive computing, but lack well-suited...

Topics: Neurons and Cognition, Computing Research Repository, Quantitative Biology, Neural and Evolutionary...

Source: http://arxiv.org/abs/1509.07302

47
47

Jun 29, 2018
06/18

by
Tejas D. Kulkarni; Ardavan Saeedi; Simanta Gautam; Samuel J. Gershman

texts

######
eye 47

######
favorite 0

######
comment 0

Learning robust value functions given raw observations and rewards is now possible with model-free and model-based deep reinforcement learning algorithms. There is a third alternative, called Successor Representations (SR), which decomposes the value function into two components -- a reward predictor and a successor map. The successor map represents the expected future state occupancy from any given state and the reward predictor maps states to scalar rewards. The value function of a state can...

Topics: Machine Learning, Artificial Intelligence, Learning, Statistics, Neural and Evolutionary Computing,...

Source: http://arxiv.org/abs/1606.02396

12
12

Jun 27, 2018
06/18

by
Sergey Zagoruyko; Nikos Komodakis

texts

######
eye 12

######
favorite 0

######
comment 0

In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-based model that is trained to account for a wide variety of changes in image appearance. To that end, we explore and study multiple neural network architectures, which are specifically adapted to this...

Topics: Computer Vision and Pattern Recognition, Learning, Computing Research Repository, Neural and...

Source: http://arxiv.org/abs/1504.03641

15
15

Jun 27, 2018
06/18

by
Thanh-Le Ha; Jan Niehues; Alex Waibel

texts

######
eye 15

######
favorite 0

######
comment 0

In this paper we combine the advantages of a model using global source sentence contexts, the Discriminative Word Lexicon, and neural networks. By using deep neural networks instead of the linear maximum entropy model in the Discriminative Word Lexicon models, we are able to leverage dependencies between different source words due to the non-linearity. Furthermore, the models for different target words can share parameters and therefore data sparsity problems are effectively reduced. By using...

Topics: Learning, Computing Research Repository, Computation and Language, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1504.07395

21
21

Jun 27, 2018
06/18

by
Shaoqiu Zheng; Junzhi Li; Andreas Janecek; Ying Tan

texts

######
eye 21

######
favorite 0

######
comment 0

This paper presents a cooperative framework for fireworks algorithm (CoFFWA). A detailed analysis of existing fireworks algorithm (FWA) and its recently developed variants has revealed that (i) the selection strategy lead to the contribution of the firework with the best fitness (core firework) for the optimization overwhelms the contributions of the rest of fireworks (non-core fireworks) in the explosion operator, (ii) the Gaussian mutation operator is not as effective as it is designed to be....

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1505.00075

11
11

Jun 28, 2018
06/18

by
Abbas Kazemipour; Min Wu; Behtash Babadi

texts

######
eye 11

######
favorite 0

######
comment 0

We consider the problem of estimating self-exciting generalized linear models from limited binary observations, where the history of the process serves as the covariate. We analyze the performance of two classes of estimators, namely the $\ell_1$-regularized maximum likelihood and greedy estimators, for a canonical self-exciting process and characterize the sampling tradeoffs required for stable recovery in the non-asymptotic regime. Our results extend those of compressed sensing for linear and...

Topics: Systems and Control, Statistics, Optimization and Control, Applications, Neural and Evolutionary...

Source: http://arxiv.org/abs/1507.03955

40
40

Jun 27, 2018
06/18

by
Behnam Neyshabur; Ryota Tomioka; Nathan Srebro

texts

######
eye 40

######
favorite 0

######
comment 0

We investigate the capacity, convexity and characterization of a general family of norm-constrained feed-forward networks.

Topics: Machine Learning, Statistics, Neural and Evolutionary Computing, Learning, Artificial Intelligence,...

Source: http://arxiv.org/abs/1503.00036

9
9.0

Jun 28, 2018
06/18

by
Malte Probst; Franz Rothlauf

texts

######
eye 9

######
favorite 0

######
comment 0

Estimation of Distribution Algorithms (EDAs) require flexible probability models that can be efficiently learned and sampled. Deep Boltzmann Machines (DBMs) are generative neural networks with these desired properties. We integrate a DBM into an EDA and evaluate the performance of this system in solving combinatorial optimization problems with a single objective. We compare the results to the Bayesian Optimization Algorithm. The performance of DBM-EDA was superior to BOA for difficult...

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1509.06535

8
8.0

Jun 28, 2018
06/18

by
Jaderick P. Pabico

texts

######
eye 8

######
favorite 0

######
comment 0

Presented in this paper is a derivation of a 2D catalytic reaction-based model to solve combinatorial optimization problems (COPs). The simulated catalytic reactions, a computational metaphor, occurs in an artificial chemical reactor that finds near-optimal solutions to COPs. The artificial environment is governed by catalytic reactions that can alter the structure of artificial molecular elements. Altering the molecular structure means finding new solutions to the COP. The molecular mass of...

Topics: Computing Research Repository, Emerging Technologies, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1506.09019

7
7.0

Jun 30, 2018
06/18

by
Casey Kneale; Dominic Poerio; Karl S. Booksh

texts

######
eye 7

######
favorite 0

######
comment 0

Optimized spatial partitioning algorithms are the corner stone of many successful experimental designs and statistical methods. Of these algorithms, the Centroidal Voronoi Tessellation (CVT) is the most widely utilized. CVT based methods require global knowledge of spatial boundaries, do not readily allow for weighted regions, have challenging implementations, and are inefficiently extended to high dimensional spaces. We describe two simple partitioning schemes based on nearest and next nearest...

Topics: Statistics, Neural and Evolutionary Computing, Computing Research Repository, Methodology

Source: http://arxiv.org/abs/1701.05553

10
10.0

Jun 26, 2018
06/18

by
Richard Evans

texts

######
eye 10

######
favorite 0

######
comment 0

Recent work has shown that dopamine-modulated STDP can solve many of the issues associated with reinforcement learning, such as the distal reward problem. Spiking neural networks provide a useful technique in implementing reinforcement learning in an embodied context as they can deal with continuous parameter spaces and as such are better at generalizing the correct behaviour to perform in a given context. In this project we implement a version of DA-modulated STDP in an embodied robot on a...

Topics: Robotics, Neural and Evolutionary Computing, Computing Research Repository

Source: http://arxiv.org/abs/1502.06096

25
25

Jun 28, 2018
06/18

by
Yasir Shoaib; Olivia Das

texts

######
eye 25

######
favorite 0

######
comment 0

In this article, artificial neural networks (ANN) are used for modeling the number of requests received by 1998 FIFA World Cup website. Modeling is done by means of time-series forecasting. The log traces of the website, available through the Internet Traffic Archive (ITA), are processed to obtain two time-series data sets that are used for finding the following measurements: requests/day and requests/second. These are modeled by training and simulating ANN. The method followed to collect and...

Topics: Distributed, Parallel, and Cluster Computing, Computing Research Repository, Neural and...

Source: http://arxiv.org/abs/1507.07204

17
17

Jun 26, 2018
06/18

by
Karol Gregor; Ivo Danihelka; Alex Graves; Danilo Jimenez Rezende; Daan Wierstra

texts

######
eye 17

######
favorite 0

######
comment 0

This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates...

Topics: Computer Vision and Pattern Recognition, Learning, Neural and Evolutionary Computing, Computing...

Source: http://arxiv.org/abs/1502.04623

9
9.0

Jun 27, 2018
06/18

by
Julien Chevallier; Maria J. Caceres; Marie Doumic; Patricia Reynaud-Bouret

texts

######
eye 9

######
favorite 0

######
comment 0

The spike trains are the main components of the information processing in the brain. To model spike trains several point processes have been investigated in the literature. And more macroscopic approaches have also been studied, using partial differential equation models. The main aim of the present article is to build a bridge between several point processes models (Poisson, Wold, Hawkes) that have been proved to statistically fit real spike trains data and age-structured partial differential...

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1506.02361

16
16

Jun 30, 2018
06/18

by
Andrea Soltoggio

texts

######
eye 16

######
favorite 0

######
comment 0

Asynchrony, overlaps and delays in sensory-motor signals introduce ambiguity as to which stimuli, actions, and rewards are causally related. Only the repetition of reward episodes helps distinguish true cause-effect relationships from coincidental occurrences. In the model proposed here, a novel plasticity rule employs short and long-term changes to evaluate hypotheses on cause-effect relationships. Transient weights represent hypotheses that are consolidated in long-term memory only when they...

Topics: Neural and Evolutionary Computing, Computing Research Repository, Quantitative Biology, Neurons and...

Source: http://arxiv.org/abs/1402.0710

10
10.0

Jun 26, 2018
06/18

by
Sergey Demyanov; James Bailey; Ramamohanarao Kotagiri; Christopher Leckie

texts

######
eye 10

######
favorite 0

######
comment 0

In many classification problems a classifier should be robust to small variations in the input vector. This is a desired property not only for particular transformations, such as translation and rotation in image classification problems, but also for all others for which the change is small enough to retain the object perceptually indistinguishable. We propose two extensions of the backpropagation algorithm that train a neural network to be robust to variations in the feature vector. While the...

Topics: Machine Learning, Learning, Statistics, Neural and Evolutionary Computing, Computing Research...

Source: http://arxiv.org/abs/1502.04434

10
10.0

Jun 27, 2018
06/18

by
Shujian Huang; Huadong Chen; Xinyu Dai; Jiajun Chen

texts

######
eye 10

######
favorite 0

######
comment 0

Modern statistical machine translation (SMT) systems usually use a linear combination of features to model the quality of each translation hypothesis. The linear combination assumes that all the features are in a linear relationship and constrains that each feature interacts with the rest features in an linear manner, which might limit the expressive power of the model and lead to a under-fit model on the current data. In this paper, we propose a non-linear modeling for the quality of...

Topics: Computing Research Repository, Computation and Language, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1503.00107

11
11

Jun 27, 2018
06/18

by
Zhen Huang; Sabato Marco Siniscalchi; I-Fan Chen; Jiadong Wu; Chin-Hui Lee

texts

######
eye 11

######
favorite 0

######
comment 0

We present a Bayesian approach to adapting parameters of a well-trained context-dependent, deep-neural-network, hidden Markov model (CD-DNN-HMM) to improve automatic speech recognition performance. Given an abundance of DNN parameters but with only a limited amount of data, the effectiveness of the adapted DNN model can often be compromised. We formulate maximum a posteriori (MAP) adaptation of parameters of a specially designed CD-DNN-HMM with an augmented linear hidden networks connected to...

Topics: Learning, Computing Research Repository, Computation and Language, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1503.02108

18
18

Jun 27, 2018
06/18

by
Y. V. Pershin; L. K. Castelano; F. Hartmann; V. Lopez-Richard; M. Di Ventra

texts

######
eye 18

######
favorite 0

######
comment 0

The original Pascaline was a mechanical calculator able to sum and subtract integers. It encodes information in the angles of mechanical wheels and through a set of gears, and aided by gravity, could perform the calculations. Here, we show that such a concept can be realized in electronics using memory elements such as memristive systems. By using memristive emulators we have demonstrated experimentally the memcomputing version of the mechanical Pascaline, capable of processing and storing the...

Topics: Condensed Matter, Mesoscale and Nanoscale Physics, Computing Research Repository, Emerging...

Source: http://arxiv.org/abs/1503.04673

5
5.0

Jun 27, 2018
06/18

by
Giacomo Parigi; Angelo Stramieri; Danilo Pau; Marco Piastra

texts

######
eye 5

######
favorite 0

######
comment 0

Among the many possible approaches for the parallelization of self-organizing networks, and in particular of growing self-organizing networks, perhaps the most common one is producing an optimized, parallel implementation of the standard sequential algorithms reported in the literature. In this paper we explore an alternative approach, based on a new algorithm variant specifically designed to match the features of the large-scale, fine-grained parallelism of GPUs, in which multiple input...

Topics: Computing Research Repository, Neural and Evolutionary Computing, Distributed, Parallel, and...

Source: http://arxiv.org/abs/1503.08294

12
12

Jun 27, 2018
06/18

by
Hongyuan Mei; Mohit Bansal; Matthew R. Walter

texts

######
eye 12

######
favorite 0

######
comment 0

We propose a neural sequence-to-sequence model for direction following, a task that is essential to realizing effective autonomous agents. Our alignment-based encoder-decoder model with long short-term memory recurrent neural networks (LSTM-RNN) translates natural language instructions to action sequences based upon a representation of the observable world state. We introduce a multi-level aligner that empowers our model to focus on sentence "regions" salient to the current world...

Topics: Computation and Language, Robotics, Artificial Intelligence, Learning, Neural and Evolutionary...

Source: http://arxiv.org/abs/1506.04089

16
16

Jun 28, 2018
06/18

by
Jayanta Basak

texts

######
eye 16

######
favorite 0

######
comment 0

Stochastic optimization is an important task in many optimization problems where the tasks are not expressible as convex optimization problems. In the case of non-convex optimization problems, various different stochastic algorithms like simulated annealing, evolutionary algorithms, and tabu search are available. Most of these algorithms require user-defined parameters specific to the problem in order to find out the optimal solution. Moreover, in many situations, iterative fine-tunings are...

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1506.08004

7
7.0

Jun 28, 2018
06/18

by
James J. Q. Yu; Victor O. K. Li

texts

######
eye 7

######
favorite 0

######
comment 0

Social Spider Algorithm (SSA) is a recently proposed general-purpose real-parameter metaheuristic designed to solve global numerical optimization problems. This work systematically benchmarks SSA on a suite of 11 functions with different control parameters. We conduct parameter sensitivity analysis of SSA using advanced non-parametric statistical tests to generate statistically significant conclusion on the best performing parameter settings. The conclusion can be adopted in future work to...

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1507.02491

12
12

Jun 28, 2018
06/18

by
Samuel Rönnqvist; Peter Sarlin

texts

######
eye 12

######
favorite 0

######
comment 0

News is a pertinent source of information on financial risks and stress factors, which nevertheless is challenging to harness due to the sparse and unstructured nature of natural text. We propose an approach based on distributional semantics and deep learning with neural networks to model and link text to a scarce set of bank distress events. Through unsupervised training, we learn semantic vector representations of news articles as predictors of distress events. The predictive model that we...

Topics: Risk Management, Quantitative Finance, Artificial Intelligence, Learning, Neural and Evolutionary...

Source: http://arxiv.org/abs/1507.07870

17
17

Jun 27, 2018
06/18

by
Tejas D. Kulkarni; Will Whitney; Pushmeet Kohli; Joshua B. Tenenbaum

texts

######
eye 17

######
favorite 0

######
comment 0

This paper presents the Deep Convolution Inverse Graphics Network (DC-IGN), a model that learns an interpretable representation of images. This representation is disentangled with respect to transformations such as out-of-plane rotations and lighting variations. The DC-IGN model is composed of multiple layers of convolution and de-convolution operators and is trained using the Stochastic Gradient Variational Bayes (SGVB) algorithm. We propose a training procedure to encourage neurons in the...

Topics: Computer Vision and Pattern Recognition, Learning, Computing Research Repository, Neural and...

Source: http://arxiv.org/abs/1503.03167

39
39

Jun 27, 2018
06/18

by
Ankit B. Patel; Tan Nguyen; Richard G. Baraniuk

texts

######
eye 39

######
favorite 0

######
comment 0

A grand challenge in machine learning is the development of computational algorithms that match or outperform humans in perceptual inference tasks that are complicated by nuisance variation. For instance, visual object recognition involves the unknown object position, orientation, and scale in object recognition while speech recognition involves the unknown voice pronunciation, pitch, and speed. Recently, a new breed of deep learning algorithms have emerged for high-nuisance inference tasks...

Topics: Machine Learning, Statistics, Computer Vision and Pattern Recognition, Neural and Evolutionary...

Source: http://arxiv.org/abs/1504.00641

17
17

Jun 27, 2018
06/18

by
Piotr Szwed; Wojciech Chmiel

texts

######
eye 17

######
favorite 0

######
comment 0

This paper presents a multi-swarm PSO algorithm for the Quadratic Assignment Problem (QAP) implemented on OpenCL platform. Our work was motivated by results of time efficiency tests performed for single-swarm algorithm implementation that showed clearly that the benefits of a parallel execution platform can be fully exploited, if the processed population is large. The described algorithm can be executed in two modes: with independent swarms or with migration. We discuss the algorithm...

Topics: Neural and Evolutionary Computing, Computing Research Repository

Source: http://arxiv.org/abs/1504.05158

6
6.0

Jun 27, 2018
06/18

by
Spyros Gidaris; Nikos Komodakis

texts

######
eye 6

######
favorite 0

######
comment 0

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization sensitivity that is essential for accurate object localization. We exploit the above properties of our recognition module by integrating it on an iterative localization mechanism that alternates...

Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Learning, Neural and...

Source: http://arxiv.org/abs/1505.01749

8
8.0

Jun 27, 2018
06/18

by
Zhipeng Wang; Mingbo Cai

texts

######
eye 8

######
favorite 0

######
comment 0

This paper extends the reinforcement learning ideas into the multi-agents system, which is far more complicated than the previously studied single-agent system. We studied two different multi-agents systems. One is the fully-connected neural network consists of multiple single neurons. Another one is the simplified mechanical arm system which is controlled by multiple neurons. We suppose that each neuron is like an agent and it can do Gibbs sampling of the posterior probability of stimulus...

Topics: Artificial Intelligence, Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1505.04150

7
7.0

Jun 27, 2018
06/18

by
Gerard David Howard; Larry Bull; Ben de Lacy Costello; Andrew Adamatzky; Ella Gale

texts

######
eye 7

######
favorite 0

######
comment 0

Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse...

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1505.04357

18
18

Jun 28, 2018
06/18

by
Daniel Martí; Mattia Rigotti; Mingoo Seok; Stefano Fusi

texts

######
eye 18

######
favorite 0

######
comment 0

Neuromorphic engineering combines the architectural and computational principles of systems neuroscience with semiconductor electronics, with the aim of building efficient and compact devices that mimic the synaptic and neural machinery of the brain. Neuromorphic engineering promises extremely low energy consumptions, comparable to those of the nervous system. However, until now the neuromorphic approach has been restricted to relatively simple circuits and specialized functions, rendering...

Topics: Neurons and Cognition, Quantitative Biology, Computing Research Repository, Neural and Evolutionary...

Source: http://arxiv.org/abs/1507.00235

11
11

Jun 27, 2018
06/18

by
William Chan; Ian Lane

texts

######
eye 11

######
favorite 0

######
comment 0

We present a novel deep Recurrent Neural Network (RNN) model for acoustic modelling in Automatic Speech Recognition (ASR). We term our contribution as a TC-DNN-BLSTM-DNN model, the model combines a Deep Neural Network (DNN) with Time Convolution (TC), followed by a Bidirectional Long Short-Term Memory (BLSTM), and a final DNN. The first DNN acts as a feature processor to our model, the BLSTM then generates a context from the sequence acoustic signal, and the final DNN takes the context and...

Topics: Machine Learning, Statistics, Neural and Evolutionary Computing, Learning, Computing Research...

Source: http://arxiv.org/abs/1504.01482

6
6.0

Jun 30, 2018
06/18

by
Zhe Yao; Vincent Gripon; Michael Rabbat

texts

######
eye 6

######
favorite 0

######
comment 0

In this paper we analyze and extend the neural network based associative memory proposed by Gripon and Berrou. This associative memory resembles the celebrated Willshaw model with an added partite cluster structure. In the literature, two retrieving schemes have been proposed for the network dynamics, namely sum-of-sum and sum-of-max. They both offer considerably better performance than Willshaw and Hopfield networks, when comparable retrieval scenarios are considered. Former discussions and...

Topics: Neural and Evolutionary Computing, Computing Research Repository

Source: http://arxiv.org/abs/1409.7758

9
9.0

Jun 26, 2018
06/18

by
Shiliang Zhang; Hui Jiang

texts

######
eye 9

######
favorite 0

######
comment 0

In this paper, we propose a novel model for high-dimensional data, called the Hybrid Orthogonal Projection and Estimation (HOPE) model, which combines a linear orthogonal projection and a finite mixture model under a unified generative modeling framework. The HOPE model itself can be learned unsupervised from unlabelled data based on the maximum likelihood estimation as well as discriminatively from labelled data. More interestingly, we have shown the proposed HOPE models are closely related to...

Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository

Source: http://arxiv.org/abs/1502.00702

13
13

Jun 27, 2018
06/18

by
Zhiguang Wang; Tim Oates

texts

######
eye 13

######
favorite 0

######
comment 0

Inspired by recent successes of deep learning in computer vision, we propose a novel framework for encoding time series as different types of images, namely, Gramian Angular Summation/Difference Fields (GASF/GADF) and Markov Transition Fields (MTF). This enables the use of techniques from computer vision for time series classification and imputation. We used Tiled Convolutional Neural Networks (tiled CNNs) on 20 standard datasets to learn high-level features from the individual and compound...

Topics: Statistics, Computing Research Repository, Learning, Machine Learning, Neural and Evolutionary...

Source: http://arxiv.org/abs/1506.00327

50
50

Jun 28, 2018
06/18

by
Ryan Lowe; Nissan Pow; Iulian Serban; Joelle Pineau

texts

######
eye 50

######
favorite 0

######
comment 0

This paper introduces the Ubuntu Dialogue Corpus, a dataset containing almost 1 million multi-turn dialogues, with a total of over 7 million utterances and 100 million words. This provides a unique resource for research into building dialogue managers based on neural language models that can make use of large amounts of unlabeled data. The dataset has both the multi-turn property of conversations in the Dialog State Tracking Challenge datasets, and the unstructured nature of interactions from...

Topics: Computation and Language, Artificial Intelligence, Computing Research Repository, Learning, Neural...

Source: http://arxiv.org/abs/1506.08909

11
11

Jun 28, 2018
06/18

by
Stéphane Doncieux; Jean Liénard; Benoît Girard; Mohamed Hamdaoui; Joël Chaskalovic

texts

######
eye 11

######
favorite 0

######
comment 0

Computational models are of increasing complexity and their behavior may in particular emerge from the interaction of different parts. Studying such models becomes then more and more difficult and there is a need for methods and tools supporting this process. Multi-objective evolutionary algorithms generate a set of trade-off solutions instead of a single optimal solution. The availability of a set of solutions that have the specificity to be optimal relative to carefully chosen objectives...

Topics: Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1507.06877

18
18

Jun 28, 2018
06/18

by
Fabio Anselmi; Lorenzo Rosasco; Cheston Tan; Tomaso Poggio

texts

######
eye 18

######
favorite 0

######
comment 0

In i-theory a typical layer of a hierarchical architecture consists of HW modules pooling the dot products of the inputs to the layer with the transformations of a few templates under a group. Such layers include as special cases the convolutional layers of Deep Convolutional Networks (DCNs) as well as the non-convolutional layers (when the group contains only the identity). Rectifying nonlinearities -- which are used by present-day DCNs -- are one of the several nonlinearities admitted by...

Topics: Computing Research Repository, Learning, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1508.01084

12
12

Jun 28, 2018
06/18

by
Yanping Huang; Sai Zhang

texts

######
eye 12

######
favorite 0

######
comment 0

Deep learning methods have shown great promise in many practical applications, ranging from speech recognition, visual object recognition, to text processing. However, most of the current deep learning methods suffer from scalability problems for large-scale applications, forcing researchers or users to focus on small-scale problems with fewer parameters. In this paper, we consider a well-known machine learning model, deep belief networks (DBNs) that have yielded impressive classification...

Topics: Statistics, Computing Research Repository, Machine Learning, Learning, Neural and Evolutionary...

Source: http://arxiv.org/abs/1508.07096

6
6.0

Jun 28, 2018
06/18

by
Jianwei Luo; Jianguo Li; Jun Wang; Zhiguo Jiang; Yurong Chen

texts

######
eye 6

######
favorite 0

######
comment 0

Recently, many researches employ middle-layer output of convolutional neural network models (CNN) as features for different visual recognition tasks. Although promising results have been achieved in some empirical studies, such type of representations still suffer from the well-known issue of semantic gap. This paper proposes so-called deep attribute framework to alleviate this issue from three aspects. First, we introduce object region proposals as intermedia to represent target images, and...

Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Learning, Neural and...

Source: http://arxiv.org/abs/1509.02470

7
7.0

Jun 28, 2018
06/18

by
Pedro Tabacof; Eduardo Valle

texts

######
eye 7

######
favorite 0

######
comment 0

Adversarial examples have raised questions regarding the robustness and security of deep neural networks. In this work we formalize the problem of adversarial images given a pretrained classifier, showing that even in the linear case the resulting optimization problem is nonconvex. We generate adversarial images using shallow and deep classifiers on the MNIST and ImageNet datasets. We probe the pixel space of adversarial images using noise of varying intensity and distribution. We bring novel...

Topics: Neural and Evolutionary Computing, Computing Research Repository

Source: http://arxiv.org/abs/1510.05328