Demonstration that a theory of cortical function (“predictive coding”) can perform bayesian inference in some tasks, with a nice related work of physiological foundations of probability distribution representation in neurons and of bayesian inference

June 21, 2017 11:57 ,

M. W. Spratling, A neural implementation of Bayesian inference based on predictive coding, Connection Science, Volume 28, 2016 – Issue 4, DOI: 10.1080/09540091.2016.1243655.

Predictive coding (PC) is a leading theory of cortical function that has previously been shown to explain a great deal of neurophysiological and psychophysical data. Here it is shown that PC can perform almost exact Bayesian inference when applied to computing with population codes. It is demonstrated that the proposed algorithm, based on PC, can: decode probability distributions encoded as noisy population codes; combine priors with likelihoods to calculate posteriors; perform cue integration and cue segregation; perform function approximation; be extended to perform hierarchical inference; simultaneously represent and reason about multiple stimuli; and perform inference with multi-modal and non-Gaussian probability distributions. PC thus provides a neural network-based method for performing probabilistic computation and provides a simple, yet comprehensive, theory of how the cerebral cortex performs Bayesian inference.

Posted in: Psycho-physiological bases of engineering , Tagged:

Insights into the sparsity of graph-SLAM (i.e., in the smoothing / optimization approach to SLAM) and a good formalization of the problem

June 21, 2017 11:43 ,

K. Khosoussi, S. Huang and G. Dissanayake, “A Sparse Separable SLAM Back-End,” in IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1536-1549, Dec. 2016. DOI: 10.1109/TRO.2016.2609394.

We propose a scalable algorithm to take advantage of the separable structure of simultaneous localization and mapping (SLAM). Separability is an overlooked structure of SLAM that distinguishes it from a generic nonlinear least-squares problem. The standard relative-pose and relative-position measurement models in SLAM are affine with respect to robot and features’ positions. Therefore, given an estimate for robot orientation, the conditionally optimal estimate for the rest of the state variables can be easily computed by solving a sparse linear least-squares problem. We propose an algorithm to exploit this intrinsic property of SLAM by stripping the problem down to its nonlinear core, while maintaining its natural sparsity. Our algorithm can be used in conjunction with any Newton-based solver and is applicable to 2-D/3-D pose-graph and feature-based SLAM. Our results suggest that iteratively solving the nonlinear core of SLAM leads to a fast and reliable convergence as compared to the state-of-the-art sparse back-ends.

Posted in: Mobile robot SLAM , Tagged:

An excellent survey of metrical SLAM (and of map representations and other issues related to SLAM) as of 2016

June 21, 2017 11:13 ,

C. Cadena et al., “Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age,” in IEEE Transactions on Robotics, vol. 32, no. 6, pp. 1309-1332, Dec. 2016. DOI: 10.1109/TRO.2016.2624754.

Simultaneous localization and mapping (SLAM) consists in the concurrent construction of a model of the environment (the map), and the estimation of the state of the robot moving within it. The SLAM community has made astonishing progress over the last 30 years, enabling large-scale real-world applications and witnessing a steady transition of this technology to industry. We survey the current state of SLAM and consider future directions. We start by presenting what is now the de-facto standard formulation for SLAM. We then review related work, covering a broad set of topics including robustness and scalability in long-term mapping, metric and semantic representations for mapping, theoretical performance guarantees, active SLAM and exploration, and other new frontiers. This paper simultaneously serves as a position paper and tutorial to those who are users of SLAM. By looking at the published research with a critical eye, we delineate open challenges and new research issues, that still deserve careful scientific investigation. The paper also contains the authors’ take on two questions that often animate discussions during robotics conferences: Do robots need SLAM? and Is SLAM solved?

Posted in: Mobile robot SLAM , Tagged: , ,

Subgraph matching (isomorphism) using GPUs for managing commonsense knowledge, and a short list of other graph problems that have had benefit from multiprocessing

June 21, 2017 10:48 ,

Ha-Nguyen Tran, Erik Cambria, Amir Hussain, Towards GPU-Based Common-Sense Reasoning: Using Fast Subgraph Matching, Cognitive Computation, December 2016, Volume 8, Issue 6, pp 1074–1086, DOI: 10.1007/s12559-016-9418-4.

Common-sense reasoning is concerned with simulating cognitive human ability to make presumptions about the type and essence of ordinary situations encountered every day. The most popular way to represent common-sense knowledge is in the form of a semantic graph. Such type of knowledge, however, is known to be rather extensive: the more concepts added in the graph, the harder and slower it becomes to apply standard graph mining techniques.In this work, we propose a new fast subgraph matching approach to overcome these issues. Subgraph matching is the task of finding all matches of a query graph in a large data graph, which is known to be a non-deterministic polynomial time-complete problem. Many algorithms have been previously proposed to solve this problem using central processing units. Here, we present a new graphics processing unit-friendly method for common-sense subgraph matching, termed GpSense, which is designed for scalable massively parallel architectures, to enable next-generation Big Data sentiment analysis and natural language processing applications.We show that GpSense outperforms state-of-the-art algorithms and efficiently answers subgraph queries on large common-sense graphs.

Posted in: Artificial Intelligence, Graph theory , Tagged: ,

Including selective attention and cortical magnification to improve computer vision

June 21, 2017 10:43 ,

Ala Aboudib, Vincent Gripon, Gilles Coppin, A Biologically Inspired Framework for Visual Information Processing and an Application on Modeling Bottom-Up Visual Attention, Cognitive Computation, December 2016, Volume 8, Issue 6, pp 1007–1026, DOI: 10.1007/s12559-016-9430-8.

An emerging trend in visual information processing is toward incorporating some interesting properties of the ventral stream in order to account for some limitations of machine learning algorithms. Selective attention and cortical magnification are two such important phenomena that have been the subject of a large body of research in recent years. In this paper, we focus on designing a new model for visual acquisition that takes these important properties into account.We propose a new framework for visual information acquisition and representation that emulates the architecture of the primate visual system by integrating features such as retinal sampling and cortical magnification while avoiding spatial deformations and other side effects produced by models that tried to implement these two features. It also explicitly integrates the notion of visual angle, which is rarely taken into account by vision models. We argue that this framework can provide the infrastructure for implementing vision tasks such as object recognition and computational visual attention algorithms.To demonstrate the utility of the proposed vision framework, we propose an algorithm for bottom-up saliency prediction implemented using the proposed architecture. We evaluate the performance of the proposed model on the MIT saliency benchmark and show that it attains state-of-the-art performance, while providing some advantages over other models.

Posted in: Computer vision, Psycho-physiological bases of engineering , Tagged:

Partially observed boolean dynamic systems

June 20, 2017 12:55 ,

M. Imani and U. M. Braga-Neto, “Maximum-Likelihood Adaptive Filter for Partially Observed Boolean Dynamical Systems,” in IEEE Transactions on Signal Processing, vol. 65, no. 2, pp. 359-371, Jan.15, 15 2017.DOI: 10.1109/TSP.2016.2614798.

We present a framework for the simultaneous estimation of state and parameters of partially observed Boolean dynamical systems (POBDS). Simultaneous state and parameter estimation is achieved through the combined use of the Boolean Kalman filter and Boolean Kalman smoother, which provide the minimum mean-square error state estimators for the POBDS model, and maximum-likelihood (ML) parameter estimation; in the presence of continuous parameters, ML estimation is performed using the expectation-maximization algorithm. The performance of the proposed ML adaptive filter is demonstrated by numerical experiments with a POBDS model of gene regulatory networks observed through noisy next-generation sequencing (RNA-seq) time series data using the well-known p53-MDM2 negative-feedback loop gene regulatory model.

Posted in: Bayesian filtering , Tagged: ,

Performing filtering on graphs instead of individual signals

June 20, 2017 12:52 ,

E. Isufi, A. Loukas, A. Simonetto and G. Leus, “Autoregressive Moving Average Graph Filtering,” in IEEE Transactions on Signal Processing, vol. 65, no. 2, pp. 274-288, Jan.15, 15 2017. DOI: 10.1109/TSP.2016.2614793.

One of the cornerstones of the field of signal processing on graphs are graph filters, direct analogs of classical filters, but intended for signals defined on graphs. This paper brings forth new insights on the distributed graph filtering problem. We design a family of autoregressive moving average (ARMA) recursions, which are able to approximate any desired graph frequency response, and give exact solutions for specific graph signal denoising and interpolation problems. The philosophy to design the ARMA coefficients independently from the underlying graph renders the ARMA graph filters suitable in static and, particularly, time-varying settings. The latter occur when the graph signal and/or graph topology are changing over time. We show that in case of a time-varying graph signal, our approach extends naturally to a two-dimensional filter, operating concurrently in the graph and regular time domain. We also derive the graph filter behavior, as well as sufficient conditions for filter stability when the graph and signal are time varying. The analytical and numerical results presented in this paper illustrate that ARMA graph filters are practically appealing for static and time-varying settings, as predicted by theoretical derivations.

Posted in: Graph theory, Probability and statistics , Tagged: , ,

On the limitations of cognitive control from the human psychological perspective

June 20, 2017 12:44 ,

Tarek Amer, Karen L. Campbell, Lynn Hasher, Cognitive Control As a Double-Edged Sword, Trends in Cognitive Sciences, Volume 20, Issue 12, 2016, Pages 905-915, ISSN 1364-6613, DOI: 10.1016/j.tics.2016.10.002.

Cognitive control, the ability to limit attention to goal-relevant information, aids performance on a wide range of laboratory tasks. However, there are many day-to-day functions which require little to no control and others which even benefit from reduced control. We review behavioral and neuroimaging evidence demonstrating that reduced control can enhance the performance of both older and, under some circumstances, younger adults. Using healthy aging as a model, we demonstrate that decreased cognitive control benefits performance on tasks ranging from acquiring and using environmental information to generating creative solutions to problems. Cognitive control is thus a double-edged sword – aiding performance on some tasks when fully engaged, and many others when less engaged.

Posted in: Psycho-physiological bases of engineering , Tagged:

A proposal that explains why the human brain seems bayesian but finds difficulties in using probabilities: because it uses sampling

June 20, 2017 11:26 ,

Adam N. Sanborn, Nick Chater, Bayesian Brains without Probabilities, Trends in Cognitive Sciences, Volume 20, Issue 12, 2016, Pages 883-893, ISSN 1364-6613, DOI: 10.1016/j.tics.2016.10.003.

Bayesian explanations have swept through cognitive science over the past two decades, from intuitive physics and causal learning, to perception, motor control and language. Yet people flounder with even the simplest probability questions. What explains this apparent paradox? How can a supposedly Bayesian brain reason so poorly with probabilities? In this paper, we propose a direct and perhaps unexpected answer: that Bayesian brains need not represent or calculate probabilities at all and are, indeed, poorly adapted to do so. Instead, the brain is a Bayesian sampler. Only with infinite samples does a Bayesian sampler conform to the laws of probability; with finite samples it systematically generates classic probabilistic reasoning errors, including the unpacking effect, base-rate neglect, and the conjunction fallacy.

Posted in: Psycho-physiological bases of engineering , Tagged:

State of the art of symbolic planning, particularly the one that optimizes some cost, and a novel approach

June 20, 2017 11:22 ,

Álvaro Torralba, Vidal Alcázar, Peter Kissmann, Stefan Edelkamp, Efficient symbolic search for cost-optimal planning, Artificial Intelligence, Volume 242, January 2017, Pages 52-79, ISSN 0004-3702, DOI: 10.1016/j.artint.2016.10.001.

In cost-optimal planning we aim to find a sequence of operators that achieve a set of goals with minimum cost. Symbolic search with Binary Decision Diagrams (BDDs) performs efficient state space exploration in terms of time and memory. This is crucial in optimal settings, in which large parts of the state space must be explored in order to prove optimality. However, the development of accurate heuristics for explicit-state search in recent years have left symbolic search techniques in a secondary place. In this article we propose two orthogonal improvements for symbolic search planning. On the one hand, we analyze and compare different methods for image computation in order to efficiently perform the successor generation on symbolic search. Image computation is the main bottleneck of symbolic search algorithms so an efficient computation is paramount for efficient symbolic search planning. On the other hand, we study how to use state-invariant constraints to prune states in symbolic search. This is essential in regression search but it is yet to be exploited in symbolic search planners. Experiments with symbolic bidirectional uniform-cost search and symbolic A ⁎ search with PDBs show remarkable performance improvements on most IPC benchmark domains. Overall, with the help of our improvements, symbolic bidirectional search outperforms explicit-state search with state-of-the-art heuristics such as LM-cut across many different domains.

Posted in: Artificial Intelligence , Tagged: