2
2.0
Jun 30, 2018
06/18
by
A. V. Eremeev; Ju. V. Kovalenko
texts
eye 2
favorite 0
comment 0
In this paper, we perform an experimental study of optimal recombination operator for makespan minimization problem on single machine with sequence-dependent setup times ($1|s_{vu}|C_{\max}$). The computational experiment on benchmark problems from TSPLIB library indicates practical applicability of optimal recombination in crossover operator of genetic algorithm for $1|s_{vu}|C_{\max}$.
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1412.5067
2
2.0
Jun 28, 2018
06/18
by
Aakash Patil; Shanlan Shen; Enyi Yao; Arindam Basu
texts
eye 2
favorite 0
comment 0
We demonstrate a low-power and compact hardware implementation of Random Feature Extractor (RFE) core. With complex tasks like Image Recognition requiring a large set of features, we show how weight reuse technique can allow to virtually expand the random features available from RFE core. Further, we show how to avoid computation cost wasted for propagating "incognizant" or redundant random features. For proof of concept, we validated our approach by using our RFE core as the first...
Topics: Neural and Evolutionary Computing, Emerging Technologies, Computing Research Repository
Source: http://arxiv.org/abs/1512.07783
11
11
Jun 29, 2018
06/18
by
Aaron van den Oord; Nal Kalchbrenner; Koray Kavukcuoglu
texts
eye 11
favorite 0
comment 0
Modeling the distribution of natural images is a landmark problem in unsupervised learning. This task requires an image model that is at once expressive, tractable and scalable. We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Our method models the discrete probability of the raw pixel values and encodes the complete set of dependencies in the image. Architectural novelties include fast two-dimensional recurrent layers and an...
Topics: Computer Vision and Pattern Recognition, Neural and Evolutionary Computing, Computing Research...
Source: http://arxiv.org/abs/1601.06759
2
2.0
Jun 30, 2018
06/18
by
Aayush Ankit; Abhronil Sengupta; Priyadarshini Panda; Kaushik Roy
texts
eye 2
favorite 0
comment 0
Neuromorphic computing using post-CMOS technologies is gaining immense popularity due to its promising abilities to address the memory and power bottlenecks in von-Neumann computing systems. In this paper, we propose RESPARC - a reconfigurable and energy efficient architecture built-on Memristive Crossbar Arrays (MCA) for deep Spiking Neural Networks (SNNs). Prior works were primarily focused on device and circuit implementations of SNNs on crossbars. RESPARC advances this by proposing a...
Topics: Emerging Technologies, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1702.06064
6
6.0
Jun 28, 2018
06/18
by
Abbas Kazemipour; Min Wu; Behtash Babadi
texts
eye 6
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
8
8.0
Jun 30, 2018
06/18
by
Abdulrahman Oladipupo Ibraheem
texts
eye 8
favorite 0
comment 0
By drawing on ideas from optimisation theory, artificial neural networks (ANN), graph embeddings and sparse representations, I develop a novel technique, termed SENNS (Sparse Extraction Neural NetworkS), aimed at addressing the feature extraction problem. The proposed method uses (preferably deep) ANNs for projecting input attribute vectors to an output space wherein pairwise distances are maximized for vectors belonging to different classes, but minimized for those belonging to the same class,...
Topics: Neural and Evolutionary Computing, Statistics, Mathematics, Computing Research Repository, Computer...
Source: http://arxiv.org/abs/1412.6749
5
5.0
Jun 30, 2018
06/18
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
9
9.0
Jun 27, 2018
06/18
by
Abhinav Tushar
texts
eye 9
favorite 0
comment 0
This paper proposes an architecture for deep neural networks with hidden layer branches that learn targets of lower hierarchy than final layer targets. The branches provide a channel for enforcing useful information in hidden layer which helps in attaining better accuracy, both for the final layer and hidden layers. The shared layers modify their weights using the gradients of all cost functions higher than the branching layer. This model provides a flexible inference system with many levels of...
Topics: Computing Research Repository, Learning, Neural and Evolutionary Computing
Source: http://arxiv.org/abs/1505.00384
2
2.0
Jun 29, 2018
06/18
by
Abhyuday Jagannatha; Hong Yu
texts
eye 2
favorite 0
comment 0
Sequence labeling for extraction of medical events and their attributes from unstructured text in Electronic Health Record (EHR) notes is a key step towards semantic understanding of EHRs. It has important applications in health informatics including pharmacovigilance and drug surveillance. The state of the art supervised machine learning models in this domain are based on Conditional Random Fields (CRFs) with features calculated from fixed context windows. In this application, we explored...
Topics: Neural and Evolutionary Computing, Computation and Language, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1606.07953
2
2.0
Jun 29, 2018
06/18
by
Abigail See; Minh-Thang Luong; Christopher D. Manning
texts
eye 2
favorite 0
comment 0
Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes. This paper examines three simple magnitude-based pruning schemes to compress NMT models, namely class-blind, class-uniform, and class-distribution, which differ in terms of how pruning thresholds are computed for the different classes of weights in the NMT architecture. We demonstrate the efficacy of weight pruning as a compression technique...
Topics: Artificial Intelligence, Computation and Language, Computing Research Repository, Neural and...
Source: http://arxiv.org/abs/1606.09274
6
6.0
Jun 30, 2018
06/18
by
Adam Erskine; J Michael Herrmann
texts
eye 6
favorite 0
comment 0
Particle Swarm Optimisation (PSO) makes use of a dynamical system for solving a search task. Instead of adding search biases in order to improve performance in certain problems, we aim to remove algorithm-induced scales by controlling the swarm with a mechanism that is scale-free except possibly for a suppression of scales beyond the system size. In this way a very promising performance is achieved due to the balance of large-scale exploration and local search. The resulting algorithm shows...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1402.6888
4
4.0
Jun 29, 2018
06/18
by
Adam Summerville; Michael Mateas
texts
eye 4
favorite 0
comment 0
The procedural generation of video game levels has existed for at least 30 years, but only recently have machine learning approaches been used to generate levels without specifying the rules for generation. A number of these have looked at platformer levels as a sequence of characters and performed generation using Markov chains. In this paper we examine the use of Long Short-Term Memory recurrent neural networks (LSTMs) for the purpose of generating levels trained from a corpus of Super Mario...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1603.00930
3
3.0
Jun 28, 2018
06/18
by
Adam Trischler; Gabriele MT D'Eleuterio
texts
eye 3
favorite 0
comment 0
We review several of the most widely used techniques for training recurrent neural networks to approximate dynamical systems, then describe a novel algorithm for this task. The algorithm is based on an earlier theoretical result that guarantees the quality of the network approximation. We show that a feedforward neural network can be trained on the vector field representation of a given dynamical system using backpropagation, then recast, using matrix manipulations, as a recurrent network that...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1512.05702
9
9.0
Jun 26, 2018
06/18
by
Adam W. Harley; Alex Ufkes; Konstantinos G. Derpanis
texts
eye 9
favorite 0
comment 0
This paper presents a new state-of-the-art for document image classification and retrieval, using features learned by deep convolutional neural networks (CNNs). In object and scene analysis, deep neural nets are capable of learning a hierarchical chain of abstraction from pixel inputs to concise and descriptive representations. The current work explores this capacity in the realm of document analysis, and confirms that this representation strategy is superior to a variety of popular...
Topics: Computer Vision and Pattern Recognition, Learning, Neural and Evolutionary Computing, Computing...
Source: http://arxiv.org/abs/1502.07058
2
2.0
Jun 29, 2018
06/18
by
Adedotun Akintayo; Kin Gwn Lore; Soumalya Sarkar; Soumik Sarkar
texts
eye 2
favorite 0
comment 0
This paper proposes an end-to-end convolutional selective autoencoder approach for early detection of combustion instabilities using rapidly arriving flame image frames. The instabilities arising in combustion processes cause significant deterioration and safety issues in various human-engineered systems such as land and air based gas turbine engines. These properties are described as self-sustaining, large amplitude pressure oscillations and show varying spatial scales periodic coherent vortex...
Topics: Computer Vision and Pattern Recognition, Neural and Evolutionary Computing, Computing Research...
Source: http://arxiv.org/abs/1603.07839
3
3.0
Jun 29, 2018
06/18
by
Adenilton J. da Silva; Wilson R. de Oliveira; Teresa B. Ludermir
texts
eye 3
favorite 0
comment 0
Training artificial neural networks requires a tedious empirical evaluation to determine a suitable neural network architecture. To avoid this empirical process several techniques have been proposed to automatise the architecture selection process. In this paper, we propose a method to perform parameter and architecture selection for a quantum weightless neural network (qWNN). The architecture selection is performed through the learning procedure of a qWNN with a learning algorithm that uses...
Topics: Quantum Physics, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1601.03277
6
6.0
Jun 29, 2018
06/18
by
Adenilton J. da Silva; Teresa B. Ludermir; Wilson R. de Oliveira
texts
eye 6
favorite 0
comment 0
In this work, we propose a quantum neural network named quantum perceptron over a field (QPF). Quantum computers are not yet a reality and the models and algorithms proposed in this work cannot be simulated in actual (or classical) computers. QPF is a direct generalization of a classical perceptron and solves some drawbacks found in previous models of quantum perceptrons. We also present a learning algorithm named Superposition based Architecture Learning algorithm (SAL) that optimizes the...
Topics: Quantum Physics, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1602.00709
2
2.0
Jun 29, 2018
06/18
by
Adham Atyabi; Martin Luerssena; Sean P. Fitzgibbon; Trent Lewis; David M. W. Powersa
texts
eye 2
favorite 0
comment 0
Training Brain Computer Interface (BCI) systems to understand the intention of a subject through Electroencephalogram (EEG) data currently requires multiple training sessions with a subject in order to develop the necessary expertise to distinguish signals for different tasks. Conventionally the task of training the subject is done by introducing a training and calibration stage during which some feedback is presented to the subject. This training session can take several hours which is not...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1602.02237
4
4.0
Jun 29, 2018
06/18
by
Adhiguna Kuncoro; Yuichiro Sawai; Kevin Duh; Yuji Matsumoto
texts
eye 4
favorite 0
comment 0
We propose a transition-based dependency parser using Recurrent Neural Networks with Long Short-Term Memory (LSTM) units. This extends the feedforward neural network parser of Chen and Manning (2014) and enables modelling of entire sequences of shift/reduce transition decisions. On the Google Web Treebank, our LSTM parser is competitive with the best feedforward parser on overall accuracy and notably achieves more than 3% improvement for long-range dependencies, which has proved difficult for...
Topics: Neural and Evolutionary Computing, Computation and Language, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1604.06529
3
3.0
Jun 30, 2018
06/18
by
Aditya Gilra; Wulfram Gerstner
texts
eye 3
favorite 0
comment 0
Brains need to predict how the body reacts to motor commands. It is an open question how networks of spiking neurons can learn to reproduce the non-linear body dynamics caused by motor commands, using local, online and stable learning rules. Here, we present a supervised learning scheme for the feedforward and recurrent connections in a network of heterogeneous spiking neurons. The error in the output is fed back through fixed random connections with a negative gain, causing the network to...
Topics: Neurons and Cognition, Learning, Computing Research Repository, Quantitative Biology, Neural and...
Source: http://arxiv.org/abs/1702.06463
3
3.0
Jun 30, 2018
06/18
by
Adnan Anwar; A. N. Mahmood
texts
eye 3
favorite 0
comment 0
Recently there has been increasing interest in improving smart grids efficiency using computational intelligence. A key challenge in future smart grid is designing Optimal Power Flow tool to solve important planning problems including optimal DG capacities. Although, a number of OPF tools exists for balanced networks there is a lack of research for unbalanced multi-phase distribution networks. In this paper, a new OPF technique has been proposed for the DG capacity planning of a smart grid....
Topics: Neural and Evolutionary Computing, Computational Engineering, Finance, and Science, Computing...
Source: http://arxiv.org/abs/1408.4849
4
4.0
Jun 30, 2018
06/18
by
Adnan Anwar; Abdun Naser Mahmood
texts
eye 4
favorite 0
comment 0
Accurate forecasting is important for cost-effective and efficient monitoring and control of the renewable energy based power generation. Wind based power is one of the most difficult energy to predict accurately, due to the widely varying and unpredictable nature of wind energy. Although Autoregressive (AR) techniques have been widely used to create wind power models, they have shown limited accuracy in forecasting, as well as difficulty in determining the correct parameters for an optimized...
Topics: Neural and Evolutionary Computing, Computational Engineering, Finance, and Science, Computing...
Source: http://arxiv.org/abs/1408.4792
4
4.0
Jun 30, 2018
06/18
by
Adriana Romero; Nicolas Ballas; Samira Ebrahimi Kahou; Antoine Chassang; Carlo Gatta; Yoshua Bengio
texts
eye 4
favorite 0
comment 0
While depth tends to improve network performances, it also makes gradient-based training more difficult since deeper networks tend to be more non-linear. The recently proposed knowledge distillation approach is aimed at obtaining small and fast-to-execute models, and it has shown that a student network could imitate the soft output of a larger teacher network or ensemble of networks. In this paper, we extend this idea to allow the training of a student that is deeper and thinner than the...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1412.6550
3
3.0
Jun 29, 2018
06/18
by
Adrien Gaidon; Qiao Wang; Yohann Cabon; Eleonora Vig
texts
eye 3
favorite 0
comment 0
Modern computer vision algorithms typically require expensive data acquisition and accurate manual labeling. In this work, we instead leverage the recent progress in computer graphics to generate fully labeled, dynamic, and photo-realistic proxy virtual worlds. We propose an efficient real-to-virtual world cloning method, and validate our approach by building and publicly releasing a new video dataset, called Virtual KITTI (see...
Topics: Computer Vision and Pattern Recognition, Machine Learning, Statistics, Learning, Neural and...
Source: http://arxiv.org/abs/1605.06457
2
2.0
Jun 30, 2018
06/18
by
Afroze Ibrahim Baqapuri; Ilya Trofimov
texts
eye 2
favorite 0
comment 0
Sponsored search is a multi-billion dollar industry and makes up a major source of revenue for search engines (SE). click-through-rate (CTR) estimation plays a crucial role for ads selection, and greatly affects the SE revenue, advertiser traffic and user experience. We propose a novel architecture for solving CTR prediction problem by combining artificial neural networks (ANN) with decision trees. First we compare ANN with respect to other popular machine learning models being used for this...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1412.6601
2
2.0
Jun 29, 2018
06/18
by
Ahmed M. Abdelsalam; J. M. Pierre Langlois; F. Cheriet
texts
eye 2
favorite 0
comment 0
Implementing an accurate and fast activation function with low cost is a crucial aspect to the implementation of Deep Neural Networks (DNNs) on FPGAs. We propose a high-accuracy approximation approach for the hyperbolic tangent activation function of artificial neurons in DNNs. It is based on the Discrete Cosine Transform Interpolation Filter (DCTIF). The proposed architecture combines simple arithmetic operations on stored samples of the hyperbolic tangent function and on input data. The...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1609.07750
3
3.0
Jun 30, 2018
06/18
by
Ahmed. H. Asad; Ahmad Taher Azar; Nashwa El-Bendary; Aboul Ella Hassaanien
texts
eye 3
favorite 0
comment 0
Features selection is an essential step for successful data classification, since it reduces the data dimensionality by removing redundant features. Consequently, that minimizes the classification complexity and time in addition to maximizing its accuracy. In this article, a comparative study considering six features selection heuristics is conducted in order to select the best relevant features subset. The tested features vector consists of fourteen features that are computed for each pixel in...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1403.1735
4
4.0
Jun 29, 2018
06/18
by
Aish Fenton
texts
eye 4
favorite 0
comment 0
In this thesis we present a new algorithm for the Vehicle Routing Problem called the Enhanced Bees Algorithm. It is adapted from a fairly recent algorithm, the Bees Algorithm, which was developed for continuous optimisation problems. We show that the results obtained by the Enhanced Bees Algorithm are competitive with the best meta-heuristics available for the Vehicle Routing Problem (within 0.5% of the optimal solution for common benchmark problems). We show that the algorithm has good runtime...
Topics: Artificial Intelligence, Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1605.05448
4
4.0
Jun 29, 2018
06/18
by
Akash Kumar Dhaka; Giampiero Salvi
texts
eye 4
favorite 0
comment 0
We present a systematic analysis on the performance of a phonetic recogniser when the window of input features is not symmetric with respect to the current frame. The recogniser is based on Context Dependent Deep Neural Networks (CD-DNNs) and Hidden Markov Models (HMMs). The objective is to reduce the latency of the system by reducing the number of future feature frames required to estimate the current output. Our tests performed on the TIMIT database show that the performance does not degrade...
Topics: Computer Vision and Pattern Recognition, Computation and Language, Machine Learning, Statistics,...
Source: http://arxiv.org/abs/1606.09163
2
2.0
Jun 29, 2018
06/18
by
Akhilesh Jaiswal; Sourjya Roy; Gopalakrishnan Srinivasan; Kaushik Roy
texts
eye 2
favorite 0
comment 0
The efficiency of the human brain in performing classification tasks has attracted considerable research interest in brain-inspired neuromorphic computing. Hardware implementations of a neuromorphic system aims to mimic the computations in the brain through interconnection of neurons and synaptic weights. A leaky-integrate-fire (LIF) spiking model is widely used to emulate the dynamics of neuronal action potentials. In this work, we propose a spin based LIF spiking neuron using the...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1609.09158
3
3.0
Jun 30, 2018
06/18
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
7
7.0
Jun 28, 2018
06/18
by
Alan Mosca; George D. Magoulas
texts
eye 7
favorite 0
comment 0
The Resilient Propagation (Rprop) algorithm has been very popular for backpropagation training of multilayer feed-forward neural networks in various applications. The standard Rprop however encounters difficulties in the context of deep neural networks as typically happens with gradient-based learning algorithms. In this paper, we propose a modification of the Rprop that combines standard Rprop steps with a special drop out technique. We apply the method for training Deep Neural Networks as...
Topics: Statistics, Learning, Machine Learning, Neural and Evolutionary Computing, Computer Vision and...
Source: http://arxiv.org/abs/1509.04612
4
4.0
Jun 30, 2018
06/18
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
Jun 30, 2018
06/18
by
Albert H. R. Ko; Robert Sabourin; Alceu S. Britto; Luiz E. S. Oliveira
texts
eye 2
favorite 0
comment 0
The Ensemble of Classifiers (EoC) has been shown to be effective in improving the performance of single classifiers by combining their outputs, and one of the most important properties involved in the selection of the best EoC from a pool of classifiers is considered to be classifier diversity. In general, classifier diversity does not occur randomly, but is generated systematically by various ensemble creation methods. By using diverse data subsets to train classifiers, these methods can...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Learning
Source: http://arxiv.org/abs/1408.2889
31
31
Jun 29, 2018
06/18
by
Albert Zeyer; Patrick Doetsch; Paul Voigtlaender; Ralf Schlüter; Hermann Ney
texts
eye 31
favorite 0
comment 0
We present a comprehensive study of deep bidirectional long short-term memory (LSTM) recurrent neural network (RNN) based acoustic models for automatic speech recognition (ASR). We study the effect of size and depth and train models of up to 8 layers. We investigate the training aspect and study different variants of optimization methods, batching, truncated backpropagation, different regularization techniques such as dropout and $L_2$ regularization, and different gradient clipping variants....
Topics: Learning, Sound, Neural and Evolutionary Computing, Computing Research Repository, Computation and...
Source: http://arxiv.org/abs/1606.06871
2
2.0
Jun 30, 2018
06/18
by
Alec Radford; Rafal Jozefowicz; Ilya Sutskever
texts
eye 2
favorite 0
comment 0
We explore the properties of byte-level recurrent language models. When given sufficient amounts of capacity, training data, and compute time, the representations learned by these models include disentangled features corresponding to high-level concepts. Specifically, we find a single unit which performs sentiment analysis. These representations, learned in an unsupervised manner, achieve state of the art on the binary subset of the Stanford Sentiment Treebank. They are also very data...
Topics: Learning, Neural and Evolutionary Computing, Computing Research Repository, Computation and Language
Source: http://arxiv.org/abs/1704.01444
2
2.0
Jun 28, 2018
06/18
by
Aleksandar Zlateski; Kisuk Lee; H. Sebastian Seung
texts
eye 2
favorite 0
comment 0
Convolutional networks (ConvNets) have become a popular approach to computer vision. It is important to accelerate ConvNet training, which is computationally costly. We propose a novel parallel algorithm based on decomposition into a set of tasks, most of which are convolutions or FFTs. Applying Brent's theorem to the task dependency graph implies that linear speedup with the number of processors is attainable within the PRAM model of parallel computation, for wide network architectures. To...
Topics: Neural and Evolutionary Computing, Learning, Computing Research Repository, Distributed, Parallel,...
Source: http://arxiv.org/abs/1510.06706
3
3.0
Jun 29, 2018
06/18
by
Alessandro Sordoni; Philip Bachman; Adam Trischler; Yoshua Bengio
texts
eye 3
favorite 0
comment 0
We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document. Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the document. Our model outperforms state-of-the-art baselines in standard machine comprehension benchmarks such as CNN news articles and the...
Topics: Computation and Language, Computing Research Repository, Neural and Evolutionary Computing
Source: http://arxiv.org/abs/1606.02245
13
13
Jun 28, 2018
06/18
by
Alessandro Sordoni; Michel Galley; Michael Auli; Chris Brockett; Yangfeng Ji; Margaret Mitchell; Jian-Yun Nie; Jianfeng Gao; Bill Dolan
texts
eye 13
favorite 0
comment 0
We present a novel response generation system that can be trained end to end on large quantities of unstructured Twitter conversations. A neural network architecture is used to address sparsity issues that arise when integrating contextual information into classic statistical models, allowing the system to take into account previous dialog utterances. Our dynamic-context generative models show consistent gains over both context-sensitive and non-context-sensitive Machine Translation and...
Topics: Computation and Language, Artificial Intelligence, Computing Research Repository, Learning, Neural...
Source: http://arxiv.org/abs/1506.06714
2
2.0
Jun 28, 2018
06/18
by
Alessandro Sordoni; Yoshua Bengio; Hossein Vahabi; Christina Lioma; Jakob G. Simonsen; Jian-Yun Nie
texts
eye 2
favorite 0
comment 0
Users may strive to formulate an adequate textual query for their information need. Search engines assist the users by presenting query suggestions. To preserve the original search intent, suggestions should be context-aware and account for the previous queries issued by the user. Achieving context awareness is challenging due to data sparsity. We present a probabilistic suggestion model that is able to account for sequences of previous queries of arbitrary lengths. Our novel hierarchical...
Topics: Computing Research Repository, Information Retrieval, Neural and Evolutionary Computing
Source: http://arxiv.org/abs/1507.02221
2
2.0
Jun 30, 2018
06/18
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
4
4.0
Jun 29, 2018
06/18
by
Alex Graves
texts
eye 4
favorite 0
comment 0
This paper introduces Adaptive Computation Time (ACT), an algorithm that allows recurrent neural networks to learn how many computational steps to take between receiving an input and emitting an output. ACT requires minimal changes to the network architecture, is deterministic and differentiable, and does not add any noise to the parameter gradients. Experimental results are provided for four synthetic problems: determining the parity of binary vectors, applying binary logic operations, adding...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1603.08983
25
25
Jun 30, 2018
06/18
by
Alex Graves; Marc G. Bellemare; Jacob Menick; Remi Munos; Koray Kavukcuoglu
texts
eye 25
favorite 0
comment 0
We introduce a method for automatically selecting the path, or syllabus, that a neural network follows through a curriculum so as to maximise learning efficiency. A measure of the amount that the network learns from each data sample is provided as a reward signal to a nonstationary multi-armed bandit algorithm, which then determines a stochastic syllabus. We consider a range of signals derived from two distinct indicators of learning progress: rate of increase in prediction accuracy, and rate...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1704.03003
4
4.0
Jun 29, 2018
06/18
by
Alex Graves
texts
eye 4
favorite 0
comment 0
The ability to backpropagate stochastic gradients through continuous latent distributions has been crucial to the emergence of variational autoencoders and stochastic gradient variational Bayes. The key ingredient is an unbiased and low-variance way of estimating gradients with respect to distribution parameters from gradients evaluated at distribution samples. The "reparameterization trick" provides a class of transforms yielding such estimators for many continuous distributions,...
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1607.05690
9
9.0
Jun 30, 2018
06/18
by
Alex Graves; Greg Wayne; Ivo Danihelka
texts
eye 9
favorite 0
comment 0
We extend the capabilities of neural networks by coupling them to external memory resources, which they can interact with by attentional processes. The combined system is analogous to a Turing Machine or Von Neumann architecture but is differentiable end-to-end, allowing it to be efficiently trained with gradient descent. Preliminary results demonstrate that Neural Turing Machines can infer simple algorithms such as copying, sorting, and associative recall from input and output examples.
Topics: Neural and Evolutionary Computing, Computing Research Repository
Source: http://arxiv.org/abs/1410.5401
3
3.0
Jun 30, 2018
06/18
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
20
20
Jun 27, 2018
06/18
by
Alex Kendall; Matthew Grimes; Roberto Cipolla
texts
eye 20
favorite 0
comment 0
We present a robust and real-time monocular six degree of freedom relocalization system. Our system trains a convolutional neural network to regress the 6-DOF camera pose from a single RGB image in an end-to-end manner with no need of additional engineering or graph optimisation. The algorithm can operate indoors and outdoors in real time, taking 5ms per frame to compute. It obtains approximately 2m and 6 degree accuracy for large scale outdoor scenes and 0.5m and 10 degree accuracy indoors....
Topics: Computer Vision and Pattern Recognition, Computing Research Repository, Robotics, Neural and...
Source: http://arxiv.org/abs/1505.07427
4
4.0
Jun 28, 2018
06/18
by
Alex Kendall; Vijay Badrinarayanan; Roberto Cipolla
texts
eye 4
favorite 0
comment 0
We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is essential for decision making. Our contribution is a practical system which is able to predict pixel-wise class labels with a measure of model uncertainty. We achieve this by Monte Carlo sampling with dropout at test time to generate a posterior distribution of...
Topics: Neural and Evolutionary Computing, Computing Research Repository, Computer Vision and Pattern...
Source: http://arxiv.org/abs/1511.02680
7
7.0
Jun 30, 2018
06/18
by
Alex Krizhevsky
texts
eye 7
favorite 0
comment 0
I present a new way to parallelize the training of convolutional neural networks across multiple GPUs. The method scales significantly better than all alternatives when applied to modern convolutional neural networks.
Topics: Distributed, Parallel, and Cluster Computing, Neural and Evolutionary Computing, Computing Research...
Source: http://arxiv.org/abs/1404.5997
3
3.0
Jun 28, 2018
06/18
by
Alexander Braylan; Mark Hollenbeck; Elliot Meyerson; Risto Miikkulainen
texts
eye 3
favorite 0
comment 0
A general approach to knowledge transfer is introduced in which an agent controlled by a neural network adapts how it reuses existing networks as it learns in a new domain. Networks trained for a new domain can improve their performance by routing activation selectively through previously learned neural structure, regardless of how or for what it was learned. A neuroevolution implementation of this approach is presented with application to high-dimensional sequential decision-making domains....
Topics: Neural and Evolutionary Computing, Computing Research Repository, Artificial Intelligence
Source: http://arxiv.org/abs/1512.01537
