Neural Computation
Latest Publications


TOTAL DOCUMENTS

3296
(FIVE YEARS 297)

H-INDEX

183
(FIVE YEARS 8)

Published By Mit Press

1530-888x, 0899-7667

2022 ◽  
pp. 1-24
Author(s):  
Kohei Ichikawa ◽  
Asaki Kataoka

Abstract Animals make efficient probabilistic inferences based on uncertain and noisy information from the outside environment. It is known that probabilistic population codes, which have been proposed as a neural basis for encoding probability distributions, allow general neural networks (NNs) to perform near-optimal point estimation. However, the mechanism of sampling-based probabilistic inference has not been clarified. In this study, we trained two types of artificial NNs, feedforward NN (FFNN) and recurrent NN (RNN), to perform sampling-based probabilistic inference. Then we analyzed and compared their mechanisms of sampling. We found that sampling in RNN was performed by a mechanism that efficiently uses the properties of dynamical systems, unlike FFNN. In addition, we found that sampling in RNNs acted as an inductive bias, enabling a more accurate estimation than in maximum a posteriori estimation. These results provide important arguments for discussing the relationship between dynamical systems and information processing in NNs.


2022 ◽  
pp. 1-44
Author(s):  
Wei Zhong Goh ◽  
Varun Ursekar ◽  
Marc W. Howard

Abstract In recent years, it has become clear that the brain maintains a temporal memory of recent events stretching far into the past. This letter presents a neutrally inspired algorithm to use a scale-invariant temporal representation of the past to predict a scale-invariant future. The result is a scale-invariant estimate of future events as a function of the time at which they are expected to occur. The algorithm is time-local, with credit assigned to the present event by observing how it affects the prediction of the future. To illustrate the potential utility of this approach, we test the model on simultaneous renewal processes with different timescales. The algorithm scales well on these problems despite the fact that the number of states needed to describe them as a Markov process grows exponentially.


2022 ◽  
pp. 1-47
Author(s):  
Mohammad Mohammadi ◽  
Peter Tino ◽  
Kerstin Bunte

Abstract The presence of manifolds is a common assumption in many applications, including astronomy and computer vision. For instance, in astronomy, low-dimensional stellar structures, such as streams, shells, and globular clusters, can be found in the neighborhood of big galaxies such as the Milky Way. Since these structures are often buried in very large data sets, an algorithm, which can not only recover the manifold but also remove the background noise (or outliers), is highly desirable. While other works try to recover manifolds either by pushing all points toward manifolds or by downsampling from dense regions, aiming to solve one of the problems, they generally fail to suppress the noise on manifolds and remove background noise simultaneously. Inspired by the collective behavior of biological ants in food-seeking process, we propose a new algorithm that employs several random walkers equipped with a local alignment measure to detect and denoise manifolds. During the walking process, the agents release pheromone on data points, which reinforces future movements. Over time the pheromone concentrates on the manifolds, while it fades in the background noise due to an evaporation procedure. We use the Markov chain (MC) framework to provide a theoretical analysis of the convergence of the algorithm and its performance. Moreover, an empirical analysis, based on synthetic and real-world data sets, is provided to demonstrate its applicability in different areas, such as improving the performance of t-distributed stochastic neighbor embedding (t-SNE) and spectral clustering using the underlying MC formulas, recovering astronomical low-dimensional structures, and improving the performance of the fast Parzen window density estimator.


2022 ◽  
pp. 1-49
Author(s):  
Tiberiu Teşileanu ◽  
Siavash Golkar ◽  
Samaneh Nasiri ◽  
Anirvan M. Sengupta ◽  
Dmitri B. Chklovskii

Abstract The brain must extract behaviorally relevant latent variables from the signals streamed by the sensory organs. Such latent variables are often encoded in the dynamics that generated the signal rather than in the specific realization of the waveform. Therefore, one problem faced by the brain is to segment time series based on underlying dynamics. We present two algorithms for performing this segmentation task that are biologically plausible, which we define as acting in a streaming setting and all learning rules being local. One algorithm is model based and can be derived from an optimization problem involving a mixture of autoregressive processes. This algorithm relies on feedback in the form of a prediction error and can also be used for forecasting future samples. In some brain regions, such as the retina, the feedback connections necessary to use the prediction error for learning are absent. For this case, we propose a second, model-free algorithm that uses a running estimate of the autocorrelation structure of the signal to perform the segmentation. We show that both algorithms do well when tasked with segmenting signals drawn from autoregressive models with piecewise-constant parameters. In particular, the segmentation accuracy is similar to that obtained from oracle-like methods in which the ground-truth parameters of the autoregressive models are known. We also test our methods on data sets generated by alternating snippets of voice recordings. We provide implementations of our algorithms at https://github.com/ttesileanu/bio-time-series.


2022 ◽  
pp. 1-27
Author(s):  
Clifford Bohm ◽  
Douglas Kirkpatrick ◽  
Arend Hintze

Abstract Deep learning (primarily using backpropagation) and neuroevolution are the preeminent methods of optimizing artificial neural networks. However, they often create black boxes that are as hard to understand as the natural brains they seek to mimic. Previous work has identified an information-theoretic tool, referred to as R, which allows us to quantify and identify mental representations in artificial cognitive systems. The use of such measures has allowed us to make previous black boxes more transparent. Here we extend R to not only identify where complex computational systems store memory about their environment but also to differentiate between different time points in the past. We show how this extended measure can identify the location of memory related to past experiences in neural networks optimized by deep learning as well as a genetic algorithm.


2022 ◽  
pp. 1-38
Author(s):  
William Paul ◽  
Armin Hadzic ◽  
Neil Joshi ◽  
Fady Alajaji ◽  
Philippe Burlina

Abstract We propose a novel method for enforcing AI fairness with respect to protected or sensitive factors. This method uses a dual strategy performing training and representation alteration (TARA) for the mitigation of prominent causes of AI bias. It includes the use of representation learning alteration via adversarial independence to suppress the bias-inducing dependence of the data representation from protected factors and training set alteration via intelligent augmentation to address bias-causing data imbalance by using generative models that allow the fine control of sensitive factors related to underrepresented populations via domain adaptation and latent space manipulation. When testing our methods on image analytics, experiments demonstrate that TARA significantly or fully debiases baseline models while outperforming competing debiasing methods that have the same amount of information—for example, with (% overall accuracy, % accuracy gap) = (78.8, 0.5) versus the baseline method's score of (71.8, 10.5) for Eye-PACS, and (73.7, 11.8) versus (69.1, 21.7) for CelebA. Furthermore, recognizing certain limitations in current metrics used for assessing debiasing performance, we propose novel conjunctive debiasing metrics. Our experiments also demonstrate the ability of these novel metrics in assessing the Pareto efficiency of the proposed methods.


2022 ◽  
pp. 1-54
Author(s):  
Doris Voina ◽  
Stefano Recanatesi ◽  
Brian Hu ◽  
Eric Shea-Brown ◽  
Stefan Mihalas

Abstract As animals adapt to their environments, their brains are tasked with processing stimuli in different sensory contexts. Whether these computations are context dependent or independent, they are all implemented in the same neural tissue. A crucial question is what neural architectures can respond flexibly to a range of stimulus conditions and switch between them. This is a particular case of flexible architecture that permits multiple related computations within a single circuit. Here, we address this question in the specific case of the visual system circuitry, focusing on context integration, defined as the integration of feedforward and surround information across visual space. We show that a biologically inspired microcircuit with multiple inhibitory cell types can switch between visual processing of the static context and the moving context. In our model, the VIP population acts as the switch and modulates the visual circuit through a disinhibitory motif. Moreover, the VIP population is efficient, requiring only a relatively small number of neurons to switch contexts. This circuit eliminates noise in videos by using appropriate lateral connections for contextual spatiotemporal surround modulation, having superior denoising performance compared to circuits where only one context is learned. Our findings shed light on a minimally complex architecture that is capable of switching between two naturalistic contexts using few switching units.


2022 ◽  
pp. 1-23
Author(s):  
Zhenghang Cui ◽  
Issei Sato

Abstract Noisy pairwise comparison feedback has been incorporated to improve the overall query complexity of interactively learning binary classifiers. The positivity comparison oracle is extensively used to provide feedback on which is more likely to be positive in a pair of data points. Because it is impossible to determine accurate labels using this oracle alone without knowing the classification threshold, existing methods still rely on the traditional explicit labeling oracle, which explicitly answers the label given a data point. The current method conducts sorting on all data points and uses explicit labeling oracle to find the classification threshold. However, it has two drawbacks: (1) it needs unnecessary sorting for label inference and (2) it naively adapts quick sort to noisy feedback. In order to avoid these inefficiencies and acquire information of the classification threshold at the same time, we propose a new pairwise comparison oracle concerning uncertainties. This oracle answers which one has higher uncertainty given a pair of data points. We then propose an efficient adaptive labeling algorithm to take advantage of the proposed oracle. In addition, we address the situation where the labeling budget is insufficient compared to the data set size. Furthermore, we confirm the feasibility of the proposed oracle and the performance of the proposed algorithm theoretically and empirically.


2022 ◽  
pp. 1-29
Author(s):  
Yancheng Lv ◽  
Lin Lin ◽  
Jie Liu ◽  
Hao Guo ◽  
Changsheng Tong

Abstract Most of the research on machine learning classification methods is based on balanced data; the research on imbalanced data classification needs improvement. Generative adversarial networks (GANs) are able to learn high-dimensional complex data distribution without relying on a prior hypothesis, which has become a hot technology in artificial intelligence. In this letter, we propose a new structure, classroom-like generative adversarial networks (CLGANs), to construct a model with multiple generators. Taking inspiration from the fact that teachers arrange teaching activities according to students' learning situation, we propose a weight allocation function to adaptively adjust the influence weight of generator loss function on discriminator loss function. All the generators work together to improve the degree of discriminator and training sample space, so that a discriminator with excellent performance is trained and applied to the tasks of imbalanced data classification. Experimental results on the Case Western Reserve University data set and 2.4 GHz Indoor Channel Measurements data set show that the data classification ability of the discriminator trained by CLGANs with multiple generators is superior to that of other imbalanced data classification models, and the optimal discriminator can be obtained by selecting the right matching scheme of the generator models.


2022 ◽  
pp. 1-30
Author(s):  
Bruno A. Santos ◽  
Rogerio M. Gomes ◽  
Xabier E. Barandiaran ◽  
Phil Husbands

Abstract A growing body of work has demonstrated the importance of ongoing oscillatory neural activity in sensory processing and the generation of sensorimotor behaviors. It has been shown, for several different brain areas, that sensory-evoked neural oscillations are generated from the modulation by sensory inputs of inherent self-sustained neural activity (SSA). This letter contributes to that strand of research by introducing a methodology to investigate how much of the sensory-evoked oscillatory activity is generated by SSA and how much is generated by sensory inputs within the context of sensorimotor behavior in a computational model. We develop an abstract model consisting of a network of three Kuramoto oscillators controlling the behavior of a simulated agent performing a categorical perception task. The effects of sensory inputs and SSAs on sensory-evoked oscillations are quantified by the cross product of velocity vectors in the phase space of the network under different conditions (disconnected without input, connected without input, and connected with input). We found that while the agent is carrying out the task, sensory-evoked activity is predominantly generated by SSA (93.10%) with much less influence from sensory inputs (6.90%). Furthermore, the influence of sensory inputs can be reduced by 10.4% (from 6.90% to 6.18%) with a decay in the agent's performance of only 2%. A dynamical analysis shows how sensory-evoked oscillations are generated from a dynamic coupling between the level of sensitivity of the network and the intensity of the input signals. This work may suggest interesting directions for neurophysiological experiments investigating how self-sustained neural activity influences sensory input processing, and ultimately affects behavior.


Sign in / Sign up

Export Citation Format

Share Document