3
3.0
Apr 3, 2017
04/17
Apr 3, 2017
by
H. Sebastian Seung; Jonathan Zung
texts
eye 3
favorite 0
comment 0
Much has been learned about plasticity of biological synapses from empirical studies. Hebbian plasticity is driven by correlated activity of presynaptic and postsynaptic neurons. Synapses that converge onto the same neuron often behave as if they compete for a fixed resource; some survive the competition while others are eliminated. To provide computational interpretations of these aspects of synaptic plasticity, we formulate unsupervised learning as a zero-sum game between Hebbian excitation...
Topics: Neural and Evolutionary Computing, Neurons and Cognition, Computing Research Repository,...
Source: http://arxiv.org/abs/1704.00646
6
6.0
Apr 3, 2017
04/17
Apr 3, 2017
by
Léo Françoso Dal Piccol Sotto; Vinícius Veloso de Melo
texts
eye 6
favorite 0
comment 0
Traditional Linear Genetic Programming (LGP) algorithms are based only on the selection mechanism to guide the search. Genetic operators combine or mutate random portions of the individuals, without knowing if the result will lead to a fitter individual. Probabilistic Model Building Genetic Programming (PMB-GP) methods were proposed to overcome this issue through a probability model that captures the structure of the fit individuals and use it to sample new individuals. This work proposes the...
Topics: Computing Research Repository, Machine Learning, Probability, Neural and Evolutionary Computing,...
Source: http://arxiv.org/abs/1704.00828
5
5.0
Apr 3, 2017
04/17
Apr 3, 2017
by
Luís F. Simões; Dario Izzo; Evert Haasdijk; A. E. Eiben
texts
eye 5
favorite 0
comment 0
The design of spacecraft trajectories for missions visiting multiple celestial bodies is here framed as a multi-objective bilevel optimization problem. A comparative study is performed to assess the performance of different Beam Search algorithms at tackling the combinatorial problem of finding the ideal sequence of bodies. Special focus is placed on the development of a new hybridization between Beam Search and the Population-based Ant Colony Optimization algorithm. An experimental evaluation...
Topics: Physics, Neural and Evolutionary Computing, Computing Research Repository, Space Physics
Source: http://arxiv.org/abs/1704.00702
2
2.0
Apr 2, 2017
04/17
Apr 2, 2017
by
Tanmay Gupta; Kevin Shih; Saurabh Singh; Derek Hoiem
texts
eye 2
favorite 0
comment 0
A grand goal of computer vision is to build systems that learn visual representations over time that can be applied to many tasks. In this paper, we investigate a vision-language embedding as a core representation and show that it leads to better cross-task transfer than standard multi-task learning. In particular, the task of visual recognition is aligned to the task of visual question answering by forcing each to use the same word-region embeddings. We show this leads to greater inductive...
Topics: Computer Vision and Pattern Recognition, Learning, Computing Research Repository, Machine Learning,...
Source: http://arxiv.org/abs/1704.00260
3
3.0
Apr 1, 2017
04/17
Apr 1, 2017
by
Robert A. Murphy
texts
eye 3
favorite 0
comment 0
As the title suggests, we will describe (and justify through the presentation of some of the relevant mathematics) prediction methodologies for sensor measurements. This exposition will mainly be concerned with the mathematics related to modeling the sensor measurements.
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.00207
5
5.0
Mar 31, 2017
03/17
Mar 31, 2017
by
Zhiguang Wang; Jianbo Yang
texts
eye 5
favorite 0
comment 0
We proposed a deep learning method for interpretable diabetic retinopathy (DR) detection. The visual-interpretable feature of the proposed method is achieved by adding the regression activation map (RAM) after the global averaging pooling layer of the convolutional networks (CNN). With RAM, the proposed model can localize the discriminative regions of an retina image to show the specific region of interest in terms of its severity level. We believe this advantage of the proposed deep learning...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1703.10757
3
3.0
Mar 31, 2017
03/17
Mar 31, 2017
by
Gerard David Howard
texts
eye 3
favorite 0
comment 0
Self-adaptive parameters are increasingly used in the field of Evolutionary Robotics, as they allow key evolutionary rates to vary autonomously in a context-sensitive manner throughout the optimisation process. A significant limitation to self-adaptive mutation is that rates can be set unfavourably, which hinders convergence. Rate restarts are typically employed to remedy this, but thus far have only been applied in Evolutionary Robotics for mutation-only algorithms. This paper focuses on the...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Robotics
Source: http://arxiv.org/abs/1703.10754
2
2.0
Mar 30, 2017
03/17
Mar 30, 2017
by
Andrea Soltoggio; Kenneth O. Stanley; Sebastian Risi
texts
eye 2
favorite 0
comment 0
Biological neural networks are systems of extraordinary computational capabilities shaped by evolution, development, and lifetime learning. The interplay of these elements leads to the emergence of adaptive behavior and intelligence, but the complexity of the whole system of interactions is an obstacle to the understanding of the key factors at play. Inspired by such intricate natural phenomena, Evolved Plastic Artificial Neural Networks (EPANNs) use simulated evolution in-silico to breed...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository
Source: http://arxiv.org/abs/1703.10371
2
2.0
Mar 30, 2017
03/17
Mar 30, 2017
by
Hyungjun Kim; Taesu Kim; Jinseok Kim; Jae-Joon Kim
texts
eye 2
favorite 0
comment 0
Artificial Neural Network computation relies on intensive vector-matrix multiplications. Recently, the emerging nonvolatile memory (NVM) crossbar array showed a feasibility of implementing such operations with high energy efficiency, thus there are many works on efficiently utilizing emerging NVM crossbar array as analog vector-matrix multiplier. However, its nonlinear I-V characteristics restrain critical design parameters, such as the read voltage and weight range, resulting in substantial...
Topics: Emerging Technologies, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.10642
5
5.0
Mar 30, 2017
03/17
Mar 30, 2017
by
Abhinav Madahar; Yuze Ma; Kunal Patel
texts
eye 5
favorite 0
comment 0
Machine learning is increasingly prevalent in stock market trading. Though neural networks have seen success in computer vision and natural language processing, they have not been as useful in stock market trading. To demonstrate the applicability of a neural network in stock trading, we made a single-layer neural network that recommends buying or selling shares of a stock by comparing the highest high of 10 consecutive days with that of the next 10 days, a process repeated for the stock's...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.10458
4
4.0
Mar 29, 2017
03/17
Mar 29, 2017
by
Albert Gatt; Emiel Krahmer
texts
eye 4
favorite 0
comment 0
This paper surveys the current state of the art in Natural Language Generation (NLG), defined as the task of generating text or speech from non-linguistic input. A survey of NLG is timely in view of the changes that the field has undergone over the past decade or so, especially in relation to new (usually data-driven) methods, as well as new applications of NLG technology. This survey therefore aims to (a) give an up-to-date synthesis of research on the core tasks in NLG and the architectures...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository,...
Source: http://arxiv.org/abs/1703.09902
2
2.0
Mar 29, 2017
03/17
Mar 29, 2017
by
Alexander Hagg
texts
eye 2
favorite 0
comment 0
Evolutionary illumination is a recent technique that allows producing many diverse, optimal solutions in a map of manually defined features. To support the large amount of objective function evaluations, surrogate model assistance was recently introduced. Illumination models need to represent many more, diverse optimal regions than classical surrogate models. In this PhD thesis, we propose to decompose the sample set, decreasing model complexity, by hierarchically segmenting the training set...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.09926
2
2.0
Mar 29, 2017
03/17
Mar 29, 2017
by
Sofia Ira Ktena; Salim Arslan; Sarah Parisot; Daniel Rueckert
texts
eye 2
favorite 0
comment 0
Data-driven brain parcellations aim to provide a more accurate representation of an individual's functional connectivity, since they are able to capture individual variability that arises due to development or disease. This renders comparisons between the emerging brain connectivity networks more challenging, since correspondences between their elements are not preserved. Unveiling these correspondences is of major importance to keep track of local functional connectivity changes. We propose a...
Topics: Quantitative Biology, Neurons and Cognition, Neural and Evolutionary Computing, Computing Research...
Source: http://arxiv.org/abs/1703.10062
5
5.0
Mar 28, 2017
03/17
Mar 28, 2017
by
Mansoureh Aghabeig; Andrzej Jaszkiewicz
texts
eye 5
favorite 0
comment 0
In this paper we systematically study the importance, i.e., the influence on performance, of the main design elements that differentiate scalarizing functions-based multiobjective evolutionary algorithms (MOEAs). This class of MOEAs includes Multiobjecitve Genetic Local Search (MOGLS) and Multiobjective Evolutionary Algorithm Based on Decomposition (MOEA/D) and proved to be very successful in multiple computational experiments and practical applications. The two algorithms share the same common...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.09469
2
2.0
Mar 28, 2017
03/17
Mar 28, 2017
by
Shengcai Liu; Ke Tang; Xin Yao
texts
eye 2
favorite 0
comment 0
This paper studies improving solvers based on their past solving experiences, and focuses on improving solvers by offline training. Specifically, the key issues of offline training methods are discussed, and research belonging to this category but from different areas are reviewed in a unified framework. Existing training methods generally adopt a two-stage strategy in which selecting the training instances and training instances are treated in two independent phases. This paper proposes a new...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.09865
2
2.0
Mar 28, 2017
03/17
Mar 28, 2017
by
Yichao Lu; Phillip Keung; Shaonan Zhang; Jason Sun; Vikas Bhardwaj
texts
eye 2
favorite 0
comment 0
We describe a prototype dialogue response generation model for the customer service domain at Amazon. The model, which is trained in a weakly supervised fashion, measures the similarity between customer questions and agent answers using a dual encoder network, a Siamese-like neural network architecture. Answer templates are extracted from embeddings derived from past agent answers, without turn-by-turn annotations. Responses to customer inquiries are generated by selecting the best template...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1703.09439
5
5.0
Mar 27, 2017
03/17
Mar 27, 2017
by
Shumeet Baluja; Ian Fischer
texts
eye 5
favorite 0
comment 0
Multiple different approaches of generating adversarial examples have been proposed to attack deep neural networks. These approaches involve either directly computing gradients with respect to the image pixels, or directly solving an optimization on the image pixels. In this work, we present a fundamentally new method for generating adversarial examples that is fast to execute and provides exceptional diversity of output. We efficiently train feed-forward neural networks in a self-supervised...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository, Computer...
Source: http://arxiv.org/abs/1703.09387
2
2.0
Mar 27, 2017
03/17
Mar 27, 2017
by
Marc Tanti; Albert Gatt; Kenneth P. Camilleri
texts
eye 2
favorite 0
comment 0
When a neural language model is used for caption generation, the image information can be fed to the neural network either by directly incorporating it in a recurrent neural network -- conditioning the language model by injecting image features -- or in a layer following the recurrent neural network -- conditioning the language model by merging the image features. While merging implies that visual features are bound at the end of the caption generation process, injecting can bind the visual...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1703.09137
10
10.0
Mar 24, 2017
03/17
Mar 24, 2017
by
Michael Fenton; James McDermott; David Fagan; Stefan Forstenlechner; Michael O'Neill; Erik Hemberg
texts
eye 10
favorite 0
comment 0
Grammatical Evolution (GE) is a population-based evolutionary algorithm, where a formal grammar is used in the genotype to phenotype mapping process. PonyGE2 is an open source implementation of GE in Python, developed at UCD's Natural Computing Research and Applications group. It is intended as an advertisement and a starting-point for those new to GE, a reference for students and researchers, a rapid-prototyping medium for our own experiments, and a Python workout. As well as providing the...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.08535
2
2.0
Mar 24, 2017
03/17
Mar 24, 2017
by
Alex C. Rollins; Jacob Schrum
texts
eye 2
favorite 0
comment 0
Previous research using evolutionary computation in Multi-Agent Systems indicates that assigning fitness based on team vs.\ individual behavior has a strong impact on the ability of evolved teams of artificial agents to exhibit teamwork in challenging tasks. However, such research only made use of single-objective evolution. In contrast, when a multiobjective evolutionary algorithm is used, populations can be subject to individual-level objectives, team-level objectives, or combinations of the...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.08577
5
5.0
Mar 24, 2017
03/17
Mar 24, 2017
by
W. B. Langdon
texts
eye 5
favorite 0
comment 0
We evolve binary mux-6 trees for up to 100000 generations evolving some programs with more than a hundred million nodes. Our unbounded Long-Term Evolution Experiment LTEE GP appears not to evolve building blocks but does suggests a limit to bloat. We do see periods of tens even hundreds of generations where the population is 100 percent functionally converged. The distribution of tree sizes is not as predicted by theory.
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.08481
3
3.0
Mar 23, 2017
03/17
Mar 23, 2017
by
Shai Shalev-Shwartz; Ohad Shamir; Shaked Shammah
texts
eye 3
favorite 0
comment 0
In recent years, Deep Learning has become the go-to solution for a broad range of applications, often outperforming state-of-the-art. However, it is important, for both theoreticians and practitioners, to gain a deeper understanding of the difficulties and limitations associated with common approaches and algorithms. We describe four types of simple problems, for which the gradient-based algorithms commonly used in deep learning either fail or suffer from significant difficulties. We illustrate...
Topics: Learning, Machine Learning, Neural and Evolutionary Computing, Statistics, Computing Research...
Source: http://arxiv.org/abs/1703.07950
3
3.0
Mar 23, 2017
03/17
Mar 23, 2017
by
Akshay Mehrotra; Ambedkar Dukkipati
texts
eye 3
favorite 0
comment 0
Deep neural networks achieve unprecedented performance levels over many tasks and scale well with large quantities of data, but performance in the low-data regime and tasks like one shot learning still lags behind. While recent work suggests many hypotheses from better optimization to more complicated network structures, in this work we hypothesize that having a learnable and more expressive similarity objective is an essential missing component. Towards overcoming that, we propose a network...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1703.08033
3
3.0
Mar 22, 2017
03/17
Mar 22, 2017
by
Ri Wang; Maysum Panju; Mahmood Gohari
texts
eye 3
favorite 0
comment 0
We report the results of our classification-based machine translation model, built upon the framework of a recurrent neural network using gated recurrent units. Unlike other RNN models that attempt to maximize the overall conditional log probability of sentences against sentences, our model focuses a classification approach of estimating the conditional probability of the next word given the input sequence. This simpler approach using GRUs was hoped to be comparable with more complicated RNN...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.07841
6
6.0
Mar 22, 2017
03/17
Mar 22, 2017
by
Kartik Audhkhasi; Bhuvana Ramabhadran; George Saon; Michael Picheny; David Nahamoo
texts
eye 6
favorite 0
comment 0
Recent work on end-to-end automatic speech recognition (ASR) has shown that the connectionist temporal classification (CTC) loss can be used to convert acoustics to phone or character sequences. Such systems are used with a dictionary and separately-trained Language Model (LM) to produce word sequences. However, they are not truly end-to-end in the sense of mapping acoustics directly to words without an intermediate phone representation. In this paper, we present the first results employing...
Topics: Machine Learning, Neural and Evolutionary Computing, Statistics, Computing Research Repository,...
Source: http://arxiv.org/abs/1703.07754
4
4.0
Mar 22, 2017
03/17
Mar 22, 2017
by
Priyadarshini Panda; Jason M. Allred; Shriram Ramanathan; Kaushik Roy
texts
eye 4
favorite 0
comment 0
A fundamental feature of learning in animals is the "ability to forget" that allows an organism to perceive, model and make decisions from disparate streams of information and adapt to changing environments. Against this backdrop, we present a novel unsupervised learning mechanism ASP (Adaptive Synaptic Plasticity) for improved recognition with Spiking Neural Networks (SNNs) for real time on-line learning in a dynamic environment. We incorporate an adaptive weight decay mechanism with...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1703.07655
2
2.0
Mar 21, 2017
03/17
Mar 21, 2017
by
Johannes Schemmel; Laura Kriener; Paul Müller; Karlheinz Meier
texts
eye 2
favorite 0
comment 0
This paper presents an extension of the BrainScaleS accelerated analog neuromorphic hardware model. The scalable neuromorphic architecture is extended by the support for multi-compartment models and non-linear dendrites. These features are part of a \SI{65}{\nano\meter} prototype ASIC. It allows to emulate different spike types observed in cortical pyramidal neurons: NMDA plateau potentials, calcium and sodium spikes. By replicating some of the structures of these cells, they can be configured...
Topics: Neural and Evolutionary Computing, Emerging Technologies, Computing Research Repository
Source: http://arxiv.org/abs/1703.07286
4
4.0
Mar 21, 2017
03/17
Mar 21, 2017
by
Alexander Hagg; Maximilian Mensing; Alexander Asteroth
texts
eye 4
favorite 0
comment 0
Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, which is important when training networks with a small number of samples. In this work we extend the neuroevolution algorithm NEAT to evolve the activation function of neurons in addition to the topology and weights of the network. The size and performance of networks produced...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.07122
2
2.0
Mar 21, 2017
03/17
Mar 21, 2017
by
Yan Duan; Marcin Andrychowicz; Bradly C. Stadie; Jonathan Ho; Jonas Schneider; Ilya Sutskever; Pieter Abbeel; Wojciech Zaremba
texts
eye 2
favorite 0
comment 0
Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In this paper, we propose a meta-learning framework for achieving such capability, which we...
Topics: Learning, Neural and Evolutionary Computing, Artificial Intelligence, Computing Research...
Source: http://arxiv.org/abs/1703.07326
2
2.0
Mar 21, 2017
03/17
Mar 21, 2017
by
Michael R. Smith; Aaron J. Hill; Kristofor D. Carlson; Craig M. Vineyard; Jonathon Donaldson; David R. Follett; Pamela L. Follett; John H. Naegle; Conrad D. James; James B. Aimone
texts
eye 2
favorite 0
comment 0
Information in neural networks is represented as weighted connections, or synapses, between neurons. This poses a problem as the primary computational bottleneck for neural networks is the vector-matrix multiply when inputs are multiplied by the neural network weights. Conventional processing architectures are not well suited for simulating neural networks, often requiring large amounts of energy and time. Additionally, synapses in biological neural networks are not binary connections, but...
Topics: Neurons and Cognition, Computing Research Repository, Machine Learning, Quantitative Biology,...
Source: http://arxiv.org/abs/1704.08306
4
4.0
Mar 21, 2017
03/17
Mar 21, 2017
by
Shumeet Baluja
texts
eye 4
favorite 0
comment 0
In all but the most trivial optimization problems, the structure of the solutions exhibit complex interdependencies between the input parameters. Decades of research with stochastic search techniques has shown the benefit of explicitly modeling the interactions between sets of parameters and the overall quality of the solutions discovered. We demonstrate a novel method, based on learning deep networks, to model the global landscapes of optimization problems. To represent the search space...
Topics: Learning, Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository
Source: http://arxiv.org/abs/1703.07394
3
3.0
Mar 20, 2017
03/17
Mar 20, 2017
by
Nadav Cohen; Ronen Tamari; Amnon Shashua
texts
eye 3
favorite 0
comment 0
The driving force behind deep networks is their ability to compactly represent rich classes of functions. The primary notion for formally reasoning about this phenomenon is expressive efficiency, which refers to a situation where one network must grow unfeasibly large in order to realize (or approximate) functions of another. To date, expressive efficiency analyses focused on the architectural feature of depth, showing that deep networks are representationally superior to shallow ones. In this...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.06846
2
2.0
Mar 20, 2017
03/17
Mar 20, 2017
by
Sebastián Basterrech
texts
eye 2
favorite 0
comment 0
The Echo State Network (ESN) is a specific recurrent network, which has gained popularity during the last years. The model has a recurrent network named reservoir, that is fixed during the learning process. The reservoir is used for transforming the input space in a larger space. A fundamental property that provokes an impact on the model accuracy is the Echo State Property (ESP). There are two main theoretical results related to the ESP. First, a sufficient condition for the ESP existence that...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.06664
5
5.0
Mar 18, 2017
03/17
Mar 18, 2017
by
Ramin M. Hasani; Victoria Beneder; Magdalena Fuchs; David Lung; Radu Grosu
texts
eye 5
favorite 0
comment 0
We introduce SIM-CE, an advanced, user-friendly modeling and simulation environment in Simulink for performing multi-scale behavioral analysis of the nervous system of Caenorhabditis elegans (C. elegans). SIM-CE contains an implementation of the mathematical models of C. elegans's neurons and synapses, in Simulink, which can be easily extended and particularized by the user. The Simulink model is able to capture both complex dynamics of ion channels and additional biophysical detail such as...
Topics: Neurons and Cognition, Quantitative Methods, Computing Research Repository, Machine Learning,...
Source: http://arxiv.org/abs/1703.06270
4
4.0
Mar 18, 2017
03/17
Mar 18, 2017
by
Johannes Thiele; Peter Diehl; Matthew Cook
texts
eye 4
favorite 0
comment 0
We investigate a recently proposed model for cortical computation which performs relational inference. It consists of several interconnected, structurally equivalent populations of leaky integrate-and-fire (LIF) neurons, which are trained in a self-organized fashion with spike-timing dependent plasticity (STDP). Despite its robust learning dynamics, the model is susceptible to a problem typical for recurrent networks which use a correlation based (Hebbian) learning rule: if trained with high...
Topics: Neural and Evolutionary Computing, Neurons and Cognition, Computing Research Repository,...
Source: http://arxiv.org/abs/1703.06290
6
6.0
Mar 18, 2017
03/17
Mar 18, 2017
by
Zhi-Zhong Liu; Yong Wang; Shengxiang Yang; Ke Tang
texts
eye 6
favorite 0
comment 0
In the evolutionary computation research community, the performance of most evolutionary algorithms (EAs) depends strongly on their implemented coordinate system. However, the commonly used coordinate system is fixed and not well suited for different function landscapes, EAs thus might not search efficiently. To overcome this shortcoming, in this paper we propose a framework, named ACoS, to adaptively tune the coordinate systems in EAs. In ACoS, an Eigen coordinate system is established by...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.06263
2
2.0
Mar 18, 2017
03/17
Mar 18, 2017
by
Ramin M. Hasani; Guodong Wang; Radu Grosu
texts
eye 2
favorite 0
comment 0
This paper studies an intelligent ultimate technique for health-monitoring and prognostic of common rotary machine components, particularly bearings. During a run-to-failure experiment, rich unsupervised features from vibration sensory data are extracted by a trained sparse auto-encoder. Then, the correlation of the extracted attributes of the initial samples (presumably healthy at the beginning of the test) with the succeeding samples is calculated and passed through a moving-average filter....
Topics: Learning, Machine Learning, Neural and Evolutionary Computing, Statistics, Computing Research...
Source: http://arxiv.org/abs/1703.06272
2
2.0
Mar 18, 2017
03/17
Mar 18, 2017
by
Ramin M. Hasani; Magdalena Fuchs; Victoria Beneder; Radu Grosu
texts
eye 2
favorite 0
comment 0
Caenorhabditis elegans (C. elegans) illustrated remarkable behavioral plasticities including complex non-associative and associative learning representations. Understanding the principles of such mechanisms presumably leads to constructive inspirations for the design of efficient learning algorithms. In the present study, we postulate a novel approach on modeling single neurons and synapses to study the mechanisms underlying learning in the C. elegans nervous system. In this regard, we...
Topics: Quantitative Biology, Neurons and Cognition, Neural and Evolutionary Computing, Computing Research...
Source: http://arxiv.org/abs/1703.06264
3
3.0
Mar 17, 2017
03/17
Mar 17, 2017
by
Ke Chen
texts
eye 3
favorite 0
comment 0
Motivated by the advantages achieved by implicit analogue net for solving online linear equations, a novel implicit neural model is designed based on conventional explicit gradient neural networks in this letter by introducing a positive-definite mass matrix. In addition to taking the advantages of the implicit neural dynamics, the proposed implicit gradient neural networks can still achieve globally exponential convergence to the unique theoretical solution of linear equations and also global...
Topics: Neural and Evolutionary Computing, Systems and Control, Computing Research Repository
Source: http://arxiv.org/abs/1703.05955
3
3.0
Mar 17, 2017
03/17
Mar 17, 2017
by
Mason McGill; Pietro Perona
texts
eye 3
favorite 0
comment 0
We propose and systematically evaluate three strategies for training dynamically-routed artificial neural networks: graphs of learned transformations through which different input signals may take different paths. Though some approaches have advantages over others, the resulting networks are often qualitatively similar. We find that, in dynamically-routed networks trained to classify images, layers and branches become specialized to process distinct categories of images. Additionally, given a...
Topics: Computer Vision and Pattern Recognition, Learning, Computing Research Repository, Machine Learning,...
Source: http://arxiv.org/abs/1703.06217
4
4.0
Mar 15, 2017
03/17
Mar 15, 2017
by
Travis Desell
texts
eye 4
favorite 0
comment 0
This work presents a new algorithm called evolutionary exploration of augmenting convolutional topologies (EXACT), which is capable of evolving the structure of convolutional neural networks (CNNs). EXACT is in part modeled after the neuroevolution of augmenting topologies (NEAT) algorithm, with notable exceptions to allow it to scale to large scale distributed computing environments and evolve networks with convolutional filters. In addition to multithreaded and MPI versions, EXACT has been...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.05422
13
13
Mar 15, 2017
03/17
Mar 15, 2017
by
Chengxun Shu; Hongyu Zhang
texts
eye 13
favorite 0
comment 0
Programming by Example (PBE) targets at automatically inferring a computer program for accomplishing a certain task from sample input and output. In this paper, we propose a deep neural networks (DNN) based PBE model called Neural Programming by Example (NPBE), which can learn from input-output strings and induce programs that solve the string manipulation problems. Our NPBE model has four neural network based components: a string encoder, an input-output analyzer, a program generator, and a...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository, Software...
Source: http://arxiv.org/abs/1703.04990
14
14
Mar 14, 2017
03/17
Mar 14, 2017
by
Thang D. Bui; Sujith Ravi; Vivek Ramavajjala
texts
eye 14
favorite 0
comment 0
Label propagation is a powerful and flexible semi-supervised learning technique on graphs. Neural networks, on the other hand, have proven track records in many supervised learning tasks. In this work, we propose a training framework with a graph-regularised objective, namely "Neural Graph Machines", that can combine the power of neural networks and label propagation. This work generalises previous literature on graph-augmented training of neural networks, enabling it to be applied to...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.04818
5
5.0
Mar 13, 2017
03/17
Mar 13, 2017
by
Vinícius Veloso de Melo; Wolfgang Banzhaf
texts
eye 5
favorite 0
comment 0
This paper proposes Drone Squadron Optimization, a new self-adaptive metaheuristic for global numerical optimization which is updated online by a hyper-heuristic. DSO is an artifact-inspired technique, as opposed to many algorithms used nowadays, which are nature-inspired. DSO is very flexible because it is not related to behaviors or natural phenomena. DSO has two core parts: the semi-autonomous drones that fly over a landscape to explore, and the Command Center that processes the retrieved...
Topics: Optimization and Control, Neural and Evolutionary Computing, Computing Research Repository,...
Source: http://arxiv.org/abs/1703.04561
3
3.0
Mar 13, 2017
03/17
Mar 13, 2017
by
Alex Kendall; Hayk Martirosyan; Saumitro Dasgupta; Peter Henry; Ryan Kennedy; Abraham Bachrach; Adam Bry
texts
eye 3
favorite 0
comment 0
We propose a novel deep learning architecture for regressing disparity from a rectified pair of stereo images. We leverage knowledge of the problem's geometry to form a cost volume using deep feature representations. We learn to incorporate contextual information using 3-D convolutions over this volume. Disparity values are regressed from the cost volume using a proposed differentiable soft argmin operation, which allows us to train our method end-to-end to sub-pixel accuracy without any...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1703.04309
3
3.0
Mar 13, 2017
03/17
Mar 13, 2017
by
Ashley Prater
texts
eye 3
favorite 0
comment 0
Echo state networks are a recently developed type of recurrent neural network where the internal layer is fixed with random weights, and only the output layer is trained on specific data. Echo state networks are increasingly being used to process spatiotemporal data in real-world settings, including speech recognition, event detection, and robot control. A strength of echo state networks is the simple method used to train the output layer - typically a collection of linear readout weights found...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1703.04496
6
6.0
Mar 13, 2017
03/17
Mar 13, 2017
by
Steven Bohez; Tim Verbelen; Elias De Coninck; Bert Vankeirsbilck; Pieter Simoens; Bart Dhoedt
texts
eye 6
favorite 0
comment 0
Deep reinforcement learning is becoming increasingly popular for robot control algorithms, with the aim for a robot to self-learn useful feature representations from unstructured sensory input leading to the optimal actuation policy. In addition to sensors mounted on the robot, sensors might also be deployed in the environment, although these might need to be accessed via an unreliable wireless connection. In this paper, we demonstrate deep neural network architectures that are able to fuse...
Topics: Learning, Neural and Evolutionary Computing, Systems and Control, Computing Research Repository,...
Source: http://arxiv.org/abs/1703.04550
2
2.0
Mar 12, 2017
03/17
Mar 12, 2017
by
Tharindu Fernando; Simon Denman; Aaron McFadyen; Sridha Sridharan; Clinton Fookes
texts
eye 2
favorite 0
comment 0
In the domain of sequence modelling, Recurrent Neural Networks (RNN) have been capable of achieving impressive results in a variety of application areas including visual question answering, part-of-speech tagging and machine translation. However this success in modelling short term dependencies has not successfully transitioned to application areas such as trajectory prediction, which require capturing both short term and long term relationships. In this paper, we propose a Tree Memory Network...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and...
Source: http://arxiv.org/abs/1703.04706
3
3.0
Mar 12, 2017
03/17
Mar 12, 2017
by
Chunpeng Wu; Wei Wen; Tariq Afzal; Yongmei Zhang; Yiran Chen; Hai Li
texts
eye 3
favorite 0
comment 0
Recently, DNN model compression based on network architecture design, e.g., SqueezeNet, attracted a lot attention. No accuracy drop on image classification is observed on these extremely compact networks, compared to well-known models. An emerging question, however, is whether these model compression techniques hurt DNN's learning ability other than classifying images on a single dataset. Our preliminary experiment shows that these compression methods could degrade domain adaptation (DA)...
Topics: Neural and Evolutionary Computing, Artificial Intelligence, Computing Research Repository, Computer...
Source: http://arxiv.org/abs/1703.04071
2
2.0
Mar 11, 2017
03/17
Mar 11, 2017
by
Hitoshi Yamamoto; Isamu Okada; Satoshi Uchida; Tatsuya Sasaki
texts
eye 2
favorite 0
comment 0
Although various norms for reciprocity-based cooperation have been suggested that are evolutionarily stable against invasion from free riders, the process of alternation of norms and the role of diversified norms remain unclear in the evolution of cooperation. We clarify the co-evolutionary dynamics of norms and cooperation in indirect reciprocity and also identify the indispensable norms for the evolution of cooperation. Inspired by the gene knockout method, a genetic engineering technique, we...
Topics: Physics, Physics and Society, Computing Research Repository, Multiagent Systems, Quantitative...
Source: http://arxiv.org/abs/1703.03943
