Topic overview

Neural and Evolutionary Computing

2839 works7829 researchers

Open map Browse papers

Map preview

Start with the graph, then narrow the list

2839works

7829researchers

Next steps

Use the topic as a working map

Open the full map for clusters, then return here to scan ranked papers and people.

Inspect nearby papers, researchers, institutions and communities without opening a separate graph page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2016arXiv

Simulated Tornado Optimization

We propose a swarm-based optimization algorithm inspired by air currents of a tornado. Two main air currents - spiral and updraft - are mimicked. Spiral motion is designed for exploration of new search areas and updraft movements is deployed for exploitation of a promising candidate solution. Assignment of just one search direction to each particle at each iteration, leads to low computational complexity of the proposed algorithm respect to the conventional algorithms. Regardless of the step size parameters, the only parameter of the proposed algorithm, called tornado diameter, can be efficiently adjusted by randomization. Numerical results over six different benchmark cost functions indicate comparable and, in some cases, better performance of the proposed algorithm respect to some other metaheuristics.

preprint2017arXiv

Deviant Learning Algorithm: Learning Sparse Mismatch Representations through Time and Space

Predictive coding (PDC) has recently attracted attention in the neuroscience and computing community as a candidate unifying paradigm for neuronal studies and artificial neural network implementations particularly targeted at unsupervised learning systems. The Mismatch Negativity (MMN) has also recently been studied in relation to PC and found to be a useful ingredient in neural predictive coding systems. Backed by the behavior of living organisms, such networks are particularly useful in forming spatio-temporal transitions and invariant representations of the input world. However, most neural systems still do not account for large number of synapses even though this has been shown by a few machine learning researchers as an effective and very important component of any neural system if such a system is to behave properly. Our major point here is that PDC systems with the MMN effect in addition to a large number of synapses can greatly improve any neural learning system's performance and ability to make decisions in the machine world. In this paper, we propose a novel bio-mimetic computational intelligence algorithm -- the Deviant Learning Algorithm, inspired by these key ideas

preprint2016arXiv

Convolutional networks and learning invariant to homogeneous multiplicative scalings

The conventional classification schemes -- notably multinomial logistic regression -- used in conjunction with convolutional networks (convnets) are classical in statistics, designed without consideration for the usual coupling with convnets, stochastic gradient descent, and backpropagation. In the specific application to supervised learning for convnets, a simple scale-invariant classification stage turns out to be more robust than multinomial logistic regression, appears to result in slightly lower errors on several standard test sets, has similar computational costs, and features precise control over the actual rate of learning. "Scale-invariant" means that multiplying the input values by any nonzero scalar leaves the output unchanged.

preprint2017arXiv

Pointer Networks

We introduce a new neural architecture to learn the conditional probability of an output sequence with elements that are discrete tokens corresponding to positions in an input sequence. Such problems cannot be trivially addressed by existent approaches such as sequence-to-sequence and Neural Turing Machines, because the number of target classes in each step of the output depends on the length of the input, which is variable. Problems such as sorting variable sized sequences, and various combinatorial optimization problems belong to this class. Our model solves the problem of variable size output dictionaries using a recently proposed mechanism of neural attention. It differs from the previous attention attempts in that, instead of using attention to blend hidden units of an encoder to a context vector at each decoder step, it uses attention as a pointer to select a member of the input sequence as the output. We call this architecture a Pointer Net (Ptr-Net). We show Ptr-Nets can be used to learn approximate solutions to three challenging geometric problems -- finding planar convex hulls, computing Delaunay triangulations, and the planar Travelling Salesman Problem -- using training

preprint2017arXiv

Visualization Regularizers for Neural Network based Image Recognition

The success of deep neural networks is mostly due their ability to learn meaningful features from the data. Features learned in the hidden layers of deep neural networks trained in computer vision tasks have been shown to be similar to mid-level vision features. We leverage this fact in this work and propose the visualization regularizer for image tasks. The proposed regularization technique enforces smoothness of the features learned by hidden nodes and turns out to be a special case of Tikhonov regularization. We achieve higher classification accuracy as compared to existing regularizers such as the L2 norm regularizer and dropout, on benchmark datasets without changing the training computational complexity.

preprint2017arXiv

Structured Sparse Convolutional Autoencoder

This paper aims to improve the feature learning in Convolutional Networks (Convnet) by capturing the structure of objects. A new sparsity function is imposed on the extracted featuremap to capture the structure and shape of the learned object, extracting interpretable features to improve the prediction performance. The proposed algorithm is based on organizing the activation within and across featuremap by constraining the node activities through $\ell_{2}$ and $\ell_{1}$ normalization in a structured form.

preprint2016arXiv

Echo State Condition at the Critical Point

Recurrent networks with transfer functions that fulfill the Lipschitz continuity with K=1 may be echo state networks if certain limitations on the recurrent connectivity are applied. It has been shown that it is sufficient if the largest singular value of the recurrent connectivity is smaller than 1. The main achievement of this paper is a proof under which conditions the network is an echo state network even if the largest singular value is one. It turns out that in this critical case the exact shape of the transfer function plays a decisive role in determining whether the network still fulfills the echo state condition. In addition, several examples with one neuron networks are outlined to illustrate effects of critical connectivity. Moreover, within the manuscript a mathematical definition for a critical echo state network is suggested.

preprint2017arXiv

How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation

We investigate evaluation metrics for dialogue response generation systems where supervised labels, such as task completion, are not available. Recent works in response generation have adopted metrics from machine translation to compare a model's generated response to a single target response. We show that these metrics correlate very weakly with human judgements in the non-technical Twitter domain, and not at all in the technical Ubuntu domain. We provide quantitative and qualitative results highlighting specific weaknesses in existing metrics, and provide recommendations for future development of better automatic evaluation metrics for dialogue systems.

preprint2016arXiv

Deep neural heart rate variability analysis

Despite of the pain and limited accuracy of blood tests for early recognition of cardiovascular disease, they dominate risk screening and triage. On the other hand, heart rate variability is non-invasive and cheap, but not considered accurate enough for clinical practice. Here, we tackle heart beat interval based classification with deep learning. We introduce an end to end differentiable hybrid architecture, consisting of a layer of biological neuron models of cardiac dynamics (modified FitzHugh Nagumo neurons) and several layers of a standard feed-forward neural network. The proposed model is evaluated on ECGs from 474 stable at-risk (coronary artery disease) patients, and 1172 chest pain patients of an emergency department. We show that it can significantly outperform models based on traditional heart rate variability predictors, as well as approaching or in some cases outperforming clinical blood tests, based only on 60 seconds of inter-beat intervals.

preprint2016arXiv

Optimization of Test Case Generation using Genetic Algorithm (GA)

Testing provides means pertaining to assuring software performance. The total aim of software industry is actually to make a certain start associated with high quality software for the end user. However, associated with software testing has quite a few underlying concerns, which are very important and need to pay attention on these issues. These issues are effectively generating, prioritization of test cases, etc. These issues can be overcome by paying attention and focus. Solitary of the greatest Problems in the software testing area is usually how to acquire a great proper set associated with cases to confirm software. Some other strategies and also methodologies are proposed pertaining to shipping care of most of these issues. Genetic Algorithm (GA) belongs to evolutionary algorithms. Evolutionary algorithms have a significant role in the automatic test generation and many researchers are focusing on it. In this study explored software testing related issues by using the GA approach. In addition to right after applying some analysis, better solution produced, that is feasible and reliable. The particular research presents the implementation of GAs because of its generation of op

preprint2016arXiv

A Basic Recurrent Neural Network Model

We present a model of a basic recurrent neural network (or bRNN) that includes a separate linear term with a slightly "stable" fixed matrix to guarantee bounded solutions and fast dynamic response. We formulate a state space viewpoint and adapt the constrained optimization Lagrange Multiplier (CLM) technique and the vector Calculus of Variations (CoV) to derive the (stochastic) gradient descent. In this process, one avoids the commonly used re-application of the circular chain-rule and identifies the error back-propagation with the co-state backward dynamic equations. We assert that this bRNN can successfully perform regression tracking of time-series. Moreover, the "vanishing and exploding" gradients are explicitly quantified and explained through the co-state dynamics and the update laws. The adapted CoV framework, in addition, can correctly and principally integrate new loss functions in the network on any variable and for varied goals, e.g., for supervised learning on the outputs and unsupervised learning on the internal (hidden) states.

preprint2016arXiv

Deep convolutional neural networks for predominant instrument recognition in polyphonic music

Identifying musical instruments in polyphonic music recordings is a challenging but important problem in the field of music information retrieval. It enables music search by instrument, helps recognize musical genres, or can make music transcription easier and more accurate. In this paper, we present a convolutional neural network framework for predominant instrument recognition in real-world polyphonic music. We train our network from fixed-length music excerpts with a single-labeled predominant instrument and estimate an arbitrary number of predominant instruments from an audio signal with a variable length. To obtain the audio-excerpt-wise result, we aggregate multiple outputs from sliding windows over the test audio. In doing so, we investigated two different aggregation methods: one takes the average for each instrument and the other takes the instrument-wise sum followed by normalization. In addition, we conducted extensive experiments on several important factors that affect the performance, including analysis window size, identification threshold, and activation functions for neural networks to find the optimal set of parameters. Using a dataset of 10k audio excerpts from 1

preprint2016arXiv

Stochastic single flux quantum neuromorphic computing using magnetically tunable Josephson junctions

Single flux quantum (SFQ) circuits form a natural neuromorphic technology with SFQ pulses and superconducting transmission lines simulating action potentials and axons, respectively. Here we present a new component, magnetic Josephson junctions, that have a tunablility and re-configurability that was lacking from previous SFQ neuromorphic circuits. The nanoscale magnetic structure acts as a tunable synaptic constituent that modifies the junction critical current. These circuits can operate near the thermal limit where stochastic firing of the neurons is an essential component of the technology. This technology has the ability to create complex neural systems with greater than 10^21 neural firings per second with approximately 1 W dissipation.

preprint2016arXiv

Convolutional Recurrent Neural Networks for Music Classification

We introduce a convolutional recurrent neural network (CRNN) for music tagging. CRNNs take advantage of convolutional neural networks (CNNs) for local feature extraction and recurrent neural networks for temporal summarisation of the extracted features. We compare CRNN with three CNN structures that have been used for music tagging while controlling the number of parameters with respect to their performance and training time per sample. Overall, we found that CRNNs show a strong performance with respect to the number of parameter and training time, indicating the effectiveness of its hybrid structure in music feature extraction and feature summarisation.

preprint2016arXiv

Predicting and visualizing psychological attributions with a deep neural network

Judgments about personality based on facial appearance are strong effectors in social decision making, and are known to have impact on areas from presidential elections to jury decisions. Recent work has shown that it is possible to predict perception of memorability, trustworthiness, intelligence and other attributes in human face images. The most successful of these approaches require face images expertly annotated with key facial landmarks. We demonstrate a Convolutional Neural Network (CNN) model that is able to perform the same task without the need for landmark features, thereby greatly increasing efficiency. The model has high accuracy, surpassing human-level performance in some cases. Furthermore, we use a deconvolutional approach to visualize important features for perception of 22 attributes and demonstrate a new method for separately visualizing positive and negative features.

preprint2016arXiv

Improving Human-Machine Cooperative Visual Search With Soft Highlighting

Advances in machine learning have produced systems that attain human-level performance on certain visual tasks, e.g., object identification. Nonetheless, other tasks requiring visual expertise are unlikely to be entrusted to machines for some time, e.g., satellite and medical imagery analysis. We describe a human-machine cooperative approach to visual search, the aim of which is to outperform either human or machine acting alone. The traditional route to augmenting human performance with automatic classifiers is to draw boxes around regions of an image deemed likely to contain a target. Human experts typically reject this type of hard highlighting. We propose instead a soft highlighting technique in which the saliency of regions of the visual field is modulated in a graded fashion based on classifier confidence level. We report on experiments with both synthetic and natural images showing that soft highlighting achieves a performance synergy surpassing that attained by hard highlighting.

preprint2016arXiv

Known Unknowns: Uncertainty Quality in Bayesian Neural Networks

We evaluate the uncertainty quality in neural networks using anomaly detection. We extract uncertainty measures (e.g. entropy) from the predictions of candidate models, use those measures as features for an anomaly detector, and gauge how well the detector differentiates known from unknown classes. We assign higher uncertainty quality to candidate models that lead to better detectors. We also propose a novel method for sampling a variational approximation of a Bayesian neural network, called One-Sample Bayesian Approximation (OSBA). We experiment on two datasets, MNIST and CIFAR10. We compare the following candidate neural network models: Maximum Likelihood, Bayesian Dropout, OSBA, and --- for MNIST --- the standard variational approximation. We show that Bayesian Dropout and OSBA provide better uncertainty information than Maximum Likelihood, and are essentially equivalent to the standard variational approximation, but much faster.

preprint2016arXiv

Data Centroid Based Multi-Level Fuzzy Min-Max Neural Network

Recently, a multi-level fuzzy min max neural network (MLF) was proposed, which improves the classification accuracy by handling an overlapped region (area of confusion) with the help of a tree structure. In this brief, an extension of MLF is proposed which defines a new boundary region, where the previously proposed methods mark decisions with less confidence and hence misclassification is more frequent. A methodology to classify patterns more accurately is presented. Our work enhances the testing procedure by means of data centroids. We exhibit an illustrative example, clearly highlighting the advantage of our approach. Results on standard datasets are also presented to evidentially prove a consistent improvement in the classification rate.

preprint2016arXiv

Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale

In recent years, the research community has discovered that deep neural networks (DNNs) and convolutional neural networks (CNNs) can yield higher accuracy than all previous solutions to a broad array of machine learning problems. To our knowledge, there is no single CNN/DNN architecture that solves all problems optimally. Instead, the "right" CNN/DNN architecture varies depending on the application at hand. CNN/DNNs comprise an enormous design space. Quantitatively, we find that a small region of the CNN design space contains 30 billion different CNN architectures. In this dissertation, we develop a methodology that enables systematic exploration of the design space of CNNs. Our methodology is comprised of the following four themes. 1. Judiciously choosing benchmarks and metrics. 2. Rapidly training CNN models. 3. Defining and describing the CNN design space. 4. Exploring the design space of CNN architectures. Taken together, these four themes comprise an effective methodology for discovering the "right" CNN architectures to meet the needs of practical applications.

preprint2016arXiv

Enabling Bio-Plausible Multi-level STDP using CMOS Neurons with Dendrites and Bistable RRAMs

Large-scale integration of emerging nanoscale non-volatile memory devices, e.g. resistive random-access memory (RRAM), can enable a new generation of neuromorphic computers that can solve a wide range of machine learning problems. Such hybrid CMOS-RRAM neuromorphic architectures will result in several orders of magnitude reduction in energy consumption at a very small form factor, and herald autonomous learning machines capable of self-adapting to their environment. However, the progress in this area has been impeded from the realization that the actual memory devices fall well short of their expected behavior. In this work, we discuss the challenges associated with these memory devices and their use in neuromorphic computing circuits, and propose pathways to overcome these limitations by introducing 'dendritic learning'.

preprint2016arXiv

Delta Networks for Optimized Recurrent Network Computation

Many neural networks exhibit stability in their activation patterns over time in response to inputs from sensors operating under real-world conditions. By capitalizing on this property of natural signals, we propose a Recurrent Neural Network (RNN) architecture called a delta network in which each neuron transmits its value only when the change in its activation exceeds a threshold. The execution of RNNs as delta networks is attractive because their states must be stored and fetched at every timestep, unlike in convolutional neural networks (CNNs). We show that a naive run-time delta network implementation offers modest improvements on the number of memory accesses and computes, but optimized training techniques confer higher accuracy at higher speedup. With these optimizations, we demonstrate a 9X reduction in cost with negligible loss of accuracy for the TIDIGITS audio digit recognition benchmark. Similarly, on the large Wall Street Journal speech recognition benchmark even existing networks can be greatly accelerated as delta networks, and a 5.7x improvement with negligible loss of accuracy can be obtained through training. Finally, on an end-to-end CNN trained for steering angl

preprint2016arXiv

Time Series Classification from Scratch with Deep Neural Networks: A Strong Baseline

We propose a simple but strong baseline for time series classification from scratch with deep neural networks. Our proposed baseline models are pure end-to-end without any heavy preprocessing on the raw data or feature crafting. The proposed Fully Convolutional Network (FCN) achieves premium performance to other state-of-the-art approaches and our exploration of the very deep neural networks with the ResNet structure is also competitive. The global average pooling in our convolutional model enables the exploitation of the Class Activation Map (CAM) to find out the contributing region in the raw data for the specific labels. Our models provides a simple choice for the real world application and a good starting point for the future research. An overall analysis is provided to discuss the generalization capability of our models, learned features, network structures and the classification semantics.

preprint2016arXiv

Towards deep learning with spiking neurons in energy based models with contrastive Hebbian plasticity

In machine learning, error back-propagation in multi-layer neural networks (deep learning) has been impressively successful in supervised and reinforcement learning tasks. As a model for learning in the brain, however, deep learning has long been regarded as implausible, since it relies in its basic form on a non-local plasticity rule. To overcome this problem, energy-based models with local contrastive Hebbian learning were proposed and tested on a classification task with networks of rate neurons. We extended this work by implementing and testing such a model with networks of leaky integrate-and-fire neurons. Preliminary results indicate that it is possible to learn a non-linear regression task with hidden layers, spiking neurons and a local synaptic plasticity rule.

preprint2016arXiv

A new cut-based genetic algorithm for graph partitioning applied to cell formation

Cell formation is a critical step in the design of cellular manufacturing systems. Recently, it was tackled using a cut-based-graph-partitioning model. This model meets real-life production systems requirements as it uses the actual amount of product flows, it looks for the suitable number of cells, and it takes into account the natural constraints such as operation sequences, maximum cell size, cohabitation and non-cohabitation constraints. Based on this model, we propose an original encoding representation to solve the problem by using a genetic algorithm. We discuss the performance of this new GA in comparison to some approaches taken from the literature on a set of medium sized instances. Given the results we obtained, it is reasonable to assume that the new GA will provide similar results for large real-life problems. Keywords: Group Technology, Manufacturing Cell Formation, Graph Partitioning, Graph Cuts, Genetic Algorithm, Encoding representation.

535 works