Search

The structure of the basal ganglia is remarkably similar across a number of species (often described in terms of direct, indirect and hyperdirect pathways) and is deeply involved in decision making and action selection. In this article, we are interested in exploring the role of structure when solving a decision task while avoiding to make any strong assumption regarding the actual structure. To do so, we exploit the echo state network paradigm that allows to solve complex task based on a random architecture. Considering a temporal decision task, the question is whether a specific structure allows for better performance and if so, whether this structure shares some similarity with the basal ganglia. Our results highlight the advantage of having a slow (direct) and a fast (hyperdirect) pathway that allows to deal with late information during a decision making task.

Using the reservoir computing framework, we demonstrate how a simple model can solve an alternation task without an explicit working memory. To do so, a simple bot equipped with sensors navigates inside a 8-shaped maze and turns alternatively right and left at the same intersection in the maze. The analysis of the model's internal activity reveals that the memory is actually encoded inside the dynamics of the network. However, such dynamic working memory is not accessible such as to bias the behavior into one of the two attractors (left and right). To do so, external cues are fed to the bot such that it can follow arbitrary sequences, instructed by the cue. This model highlights the idea that procedural learning and its internal representation can be dissociated. If the former allows to produce behavior, it is not sufficient to allow for an explicit and fine-grained manipulation., Comment: 6 pages, 7 figures, conference

We propose a variation of the self organizing map algorithm by considering the random placement of neurons on a two-dimensional manifold, following a blue noise distribution from which various topologies can be derived. These topologies possess random (but controllable) discontinuities that allow for a more flexible self-organization, especially with high-dimensional data. The proposed algorithm is tested on one-, two- and three-dimensions tasks as well as on the MNIST handwritten digits dataset and validated using spectral analysis and topological data analysis tools. We also demonstrate the ability of the randomized self-organizing map to gracefully reorganize itself in case of neural lesion and/or neurogenesis., Comment: 32 pages, 19 figures

Text editors are written by and for developers. They come with a large set of default and implicit choices in terms of layout, typography, colorization and interaction that hardly change from one editor to the other. It is not clear if these implicit choices derive from the ignorance of alternatives or if they derive from developers' habits, reproducing what they are used to. The goal of this article is to characterize these implicit choices and to illustrate what are some alternatives without prescribing one or the other., Comment: 5 pages, 5 figures, conference

We introduce a recurrent neural network model of working memory combining short-term and long-term components. e short-term component is modelled using a gated reservoir model that is trained to hold a value from an input stream when a gate signal is on. e long-term component is modelled using conceptors in order to store inner temporal patterns (that corresponds to values). We combine these two components to obtain a model where information can go from long-term memory to short-term memory and vice-versa and we show how standard operations on conceptors allow to combine long-term memories and describe their effect on short-term memory.

We introduce a general method to extract knowledge from a recurrent neural network (Long Short Term Memory) that has learnt to detect if a given input sequence is valid or not, according to an unknown generative automaton. Based on the clustering of the hidden states, we explain how to build and validate an automaton that corresponds to the underlying (unknown) automaton, and allows to predict if a given sequence is valid or not. The method is illustrated on artificial grammars (Reber's grammar variations) as well as on a real use-case whose underlying grammar is unknown., Comment: 18 pages, 17 figures

Software is a fundamental pillar of modern scientiic research, not only in computer science, but actually across all elds and disciplines. However, there is a lack of adequate means to cite and reference software, for many reasons. An obvious rst reason is software authorship, which can range from a single developer to a whole team, and can even vary in time. The panorama is even more complex than that, because many roles can be involved in software development: software architect, coder, debugger, tester, team manager, and so on. Arguably, the researchers who have invented the key algorithms underlying the software can also claim a part of the authorship. And there are many other reasons that make this issue complex. We provide in this paper a contribution to the ongoing eeorts to develop proper guidelines and recommendations for software citation, building upon the internal experience of Inria, the French research institute for digital sciences. As a central contribution, we make three key recommendations. (1) We propose a richer taxonomy for software contributions with a qualitative scale. (2) We claim that it is essential to put the human at the heart of the evaluation. And (3) we propose to distinguish citation from reference.

This paper presents the self-organized neuromorphic architecture named SOMA. The objective is to study neural-based self-organization in computing systems and to prove the feasibility of a self-organizing hardware structure. Considering that these properties emerge from large scale and fully connected neural maps, we will focus on the definition of a self-organizing hardware architecture based on digital spiking neurons that offer hardware efficiency. From a biological point of view, this corresponds to a combination of the so-called synaptic and structural plasticities. We intend to define computational models able to simultaneously self-organize at both computation and communication levels, and we want these models to be hardware-compliant, fault tolerant and scalable by means of a neuro-cellular structure., Comment: Published in IEEE World Congress on Computational Intelligence (WCCI), International Workshop: Neuromorphic Hardware in Practice and Use (NHPU), Jul. 2018, Rio de Janeiro, Brazil

The prefrontal cortex is known to be involved in many high-level cognitive functions, in particular, working memory. Here, we study to what extent a group of randomly connected units (namely an Echo State Network, ESN) can store and maintain (as output) an arbitrary real value from a streamed input, i.e. can act as a sustained working memory unit. Furthermore, we explore to what extent such an architecture can take advantage of the stored value in order to produce non-linear computations. Comparison between different architectures (with and without feedback, with and without a working memory unit) shows that an explicit memory improves the performances.

We introduce a graphical method originating from the computer graphics domain that is used for the arbitrary and intuitive placement of cells over a two-dimensional manifold. Using a bitmap image as input, where the color indicates the identity of the different structures and the alpha channel indicates the local cell density, this method guarantees a discrete distribution of cell position respecting the local density function. This method scales to any number of cells, allows to specify several different structures at once with arbitrary shapes and provides a scalable and versatile alternative to the more classical assumption of a uniform non-spatial distribution. Furthermore, several connection schemes can be derived from the paired distances between cells using either an automatic mapping or a user-defined local reference frame, providing new computational properties for the underlying model. The method is illustrated on a discrete homogeneous neural field, on the distribution of cones and rods in the retina and on a coronal view of the basal ganglia., Comment: Corresponding code at https://github.com/rougier/spatial-computation

Scientific code is not production software. Scientific code participates in the evaluation of a scientific hypothesis. This imposes specific constraints on the code that are often overlooked in practice. We articulate, with a small example, five characteristics that a scientific code in computational science should possess: re-runnable, repeatable, reproducible, reusable and replicable., Comment: Frontiers in Neuroinformatics, Frontiers, In press

Computer science offers a large set of tools for prototyping, writing, running, testing, validating, sharing and reproducing results, however computational science lags behind. In the best case, authors may provide their source code as a compressed archive and they may feel confident their research is reproducible. But this is not exactly true. James Buckheit and David Donoho proposed more than two decades ago that an article about computational results is advertising, not scholarship. The actual scholarship is the full software environment, code, and data that produced the result. This implies new workflows, in particular in peer-reviews. Existing journals have been slow to adapt: source codes are rarely requested, hardly ever actually executed to check that they produce the results advertised in the article. ReScience is a peer-reviewed journal that targets computational research and encourages the explicit replication of already published research, promoting new and open-source implementations in order to ensure that the original research can be replicated from its description. To achieve this goal, the whole publishing chain is radically different from other traditional scientific journals. ReScience resides on GitHub where each new implementation of a computational study is made available together with comments, explanations, and software tests., Comment: 8 pages, 1 figure

Popular computational models of visual attention tend to neglect the influence of saccadic eye movements whereas it has been shown that the primates perform on average three of them per seconds and that the neural substrate for the deployment of attention and the execution of an eye movement might considerably overlap. Here we propose a computational model in which the deployment of attention with or without a subsequent eye movement emerges from local, distributed and numerical computations.

Some visual search tasks require to memorize the location of stimuli that have been previously scanned. Considerations about the eye movements raise the question of how we are able to maintain a coherent memory, despite the frequent drastically changes in the perception. In this article, we present a computational model that is able to anticipate the consequences of the eye movements on the visual perception in order to update a spatial memory