Sequence Learning in a Single Trial: A Spiking Neurons Model Based on Hippocampal Circuitry

In contrast with our everyday experience using brain circuits, it can take a prohibitively long time to train a computational system to produce the correct sequence of outputs in the presence of a series of inputs. This suggests that something important is missing in the way in which models are trying to reproduce basic cognitive functions. In this work, we introduce a new neuronal network architecture that is able to learn, in a single trial, an arbitrary long sequence of any known objects. The key point of the model is the explicit use of mechanisms and circuitry observed in the hippocampus, which allow the model to reach a level of efficiency and accuracy that, to the best of our knowledge, is not possible with abstract network implementations. By directly following the natural system's layout and circuitry, this type of implementation has the additional advantage that the results can be more easily compared to the experimental data, allowing a deeper and more direct understanding of the mechanisms underlying cognitive functions and dysfunctions and opening the way to a new generation of learning architectures.

A Brain-Inspired Approach for Collision-Free Movement Planning in the Small Operational Space

In a small operational space, e.g., mesoscale or microscale, we need to control movements carefully because of fragile objects. This article proposes a novel structure based on spiking neural networks to imitate the joint function of multiple brain regions in visual guiding in the small operational space and offers two channels to achieve collision-free movements. For the state sensation, we simulate the primary visual cortex to directly extract features from multiple input images and the high-level visual cortex to obtain the object distance, which is indirectly measurable, in the Cartesian coordinates. Our approach emulates the prefrontal cortex from two aspects: multiple liquid state machines to predict distances of the next several steps based on the preceding trajectory and a block-based excitation-inhibition feedforward network to plan movements considering the target and prediction. Responding to "too close" states needs rich temporal information, and we leverage a cerebellar network for the subconscious reaction. From the viewpoint of the inner pathway, they also form two channels. One channel starts from state extraction to attraction movement planning, both in the camera coordinates, behaving visual-servo control. The other is the collision-avoidance channel, which calculates distances, predicts trajectories, and reacts to the repulsion, all in the Cartesian coordinates. We provide appropriate supervised signals for coarse training and apply reinforcement learning to modify synapses in accordance with reality. Simulation and experiment results validate the proposed method.

Implementation of Explosion Safety Regulations in Design of a Mobile Robot for Coal Mines

The article focuses on specific challenges of the design of a reconnaissance mobile robotic system aimed for inspection in underground coal mine areas after a catastrophic event. Systems that are designated for these conditions must meet specific standards and regulations. In this paper is discussed primarily the main conception of meeting explosion safety regulations of European Union 2014/34/EU (also called ATEX—from French “Appareils destinés à être utilisés en ATmosphères Explosives”) for Group I (equipment intended for use in underground mines) and Category M1 (equipment designed for operation in the presence of an explosive atmosphere). An example of a practical solution is described on main subsystems of the mobile robot TeleRescuer—a teleoperated robot with autonomy functions, a sensory subsystem with multiple cameras, three-dimensional (3D) mapping and sensors for measurement of gas concentration, airflow, relative humidity, and temperatures. Explosion safety is ensured according to the Technical Report CLC/TR 60079-33 “s” by two main independent protections—mechanical protection (flameproof enclosure) and electrical protection (automatic methane detector that disconnects power when methane breaches the enclosure and gets inside the robot body).

A Survey of Robotics Control Based on Learning-Inspired Spiking Neural Networks

Biological intelligence processes information using impulses or spikes, which makes those living creatures able to perceive and act in the real world exceptionally well and outperform state-of-the-art robots in almost every aspect of life. To make up the deficit, emerging hardware technologies and software knowledge in the fields of neuroscience, electronics, and computer science have made it possible to design biologically realistic robots controlled by spiking neural networks (SNNs), inspired by the mechanism of brains. However, a comprehensive review on controlling robots based on SNNs is still missing. In this paper, we survey the developments of the past decade in the field of spiking neural networks for control tasks, with particular focus on the fast emerging robotics-related applications. We first highlight the primary impetuses of SNN-based robotics tasks in terms of speed, energy efficiency, and computation capabilities. We then classify those SNN-based robotic applications according to different learning rules and explicate those learning rules with their corresponding robotic applications. We also briefly present some existing platforms that offer an interaction between SNNs and robotics simulations for exploration and exploitation. Finally, we conclude our survey with a forecast of future challenges and some associated potential research topics in terms of controlling robots based on SNNs.

Bio-inspired spiking neural network for nonlinear systems control

Spiking neural networks (SNN) are the third generation of artificial neural networks. SNN are the closest approximation to biological neural networks. SNNs make use of temporal spike trains to command inputs and outputs, allowing a faster and more complex computation. As demonstrated by biological organisms, they are a potentially good approach to designing controllers for highly nonlinear dynamic systems in which the performance of controllers developed by conventional techniques is not satisfactory or difficult to implement. SNN-based controllers exploit their ability for online learning and self-adaptation to evolve when transferred from simulations to the real world. SNN's inherent binary and temporary way of information codification facilitates their hardware implementation compared to analog neurons. Biological neural networks often require a lower number of neurons compared to other controllers based on artificial neural networks. In this work, these neuronal systems are imitated to perform the control of non-linear dynamic systems. For this purpose, a control structure based on spiking neural networks has been designed. Particular attention has been paid to optimizing the structure and size of the neural network. The proposed structure is able to control dynamic systems with a reduced number of neurons and connections. A supervised learning process using evolutionary algorithms has been carried out to perform controller training. The efficiency of the proposed network has been verified in two examples of dynamic systems control. Simulations show that the proposed control based on SNN exhibits superior performance compared to other approaches based on Neural Networks and SNNs.

Trajectory Correction and Locomotion Analysis of a Hexapod Walking Robot with Semi-Round Rigid Feet

Aimed at solving the misplaced body trajectory problem caused by the rolling of semi-round rigid feet when a robot is walking, a legged kinematic trajectory correction methodology based on the Least Squares Support Vector Machine (LS-SVM) is proposed. The concept of ideal foothold is put forward for the three-dimensional kinematic model modification of a robot leg, and the deviation value between the ideal foothold and real foothold is analyzed. The forward/inverse kinematic solutions between the ideal foothold and joint angular vectors are formulated and the problem of direct/inverse kinematic nonlinear mapping is solved by using the LS-SVM. Compared with the previous approximation method, this correction methodology has better accuracy and faster calculation speed with regards to inverse kinematics solutions. Experiments on a leg platform and a hexapod walking robot are conducted with multi-sensors for the analysis of foot tip trajectory, base joint vibration, contact force impact, direction deviation, and power consumption, respectively. The comparative analysis shows that the trajectory correction methodology can effectively correct the joint trajectory, thus eliminating the contact force influence of semi-round rigid feet, significantly improving the locomotion of the walking robot and reducing the total power consumption of the system.

A Fly-Inspired Mushroom Bodies Model for Sensory-Motor Control Through Sequence and Subsequence Learning

Classification and sequence learning are relevant capabilities used by living beings to extract complex information from the environment for behavioral control. The insect world is full of examples where the presentation time of specific stimuli shapes the behavioral response. On the basis of previously developed neural models, inspired by Drosophila melanogaster, a new architecture for classification and sequence learning is here presented under the perspective of the Neural Reuse theory. Classification of relevant input stimuli is performed through resonant neurons, activated by the complex dynamics generated in a lattice of recurrent spiking neurons modeling the insect Mushroom Bodies neuropile. The network devoted to context formation is able to reconstruct the learned sequence and also to trace the subsequences present in the provided input. A sensitivity analysis to parameter variation and noise is reported. Experiments on a roving robot are reported to show the capabilities of the architecture used as a neural controller.

Operant conditioning: a minimal components requirement in artificial spiking neurons designed for bio-inspired robot's controller

In this paper, we investigate the operant conditioning (OC) learning process within a bio-inspired paradigm, using artificial spiking neural networks (ASNN) to act as robot brain controllers. In biological agents, OC results in behavioral changes learned from the consequences of previous actions, based on progressive prediction adjustment from rewarding or punishing signals. In a neurorobotics context, virtual and physical autonomous robots may benefit from a similar learning skill when facing unknown and unsupervised environments. In this work, we demonstrate that a simple invariant micro-circuit can sustain OC in multiple learning scenarios. The motivation for this new OC implementation model stems from the relatively complex alternatives that have been described in the computational literature and recent advances in neurobiology. Our elementary kernel includes only a few crucial neurons, synaptic links and originally from the integration of habituation and spike-timing dependent plasticity as learning rules. Using several tasks of incremental complexity, our results show that a minimal neural component set is sufficient to realize many OC procedures. Hence, with the proposed OC module, designing learning tasks with an ASNN and a bio-inspired robot context leads to simpler neural architectures for achieving complex behaviors.

A GENERALIZED LEAKY INTEGRATE-AND-FIRE NEURON MODEL WITH FAST IMPLEMENTATION METHOD

This study introduces a new Generalized Leaky Integrate-and-Fire (GLIF) neuron model with variable leaking resistor and bias current in order to reproduce accurately the membrane voltage dynamics of a biological neuron. The accuracy of this model is ensured by adjusting its parameters to the statistical properties of the Hodgkin–Huxley model outputs; while the speed is enhanced by introducing a Generalized Exponential Moving Average method that converts the parameterized kernel functions into pre-calculated lookup tables based on an analytic solution of the dynamic equations of the GLIF model.

Spike-timing-dependent construction

Spike-timing-dependent construction (STDC) is the production of new spiking neurons and connections in a simulated neural network in response to neuron activity. Following the discovery of spike-timing-dependent plasticity (STDP), significant effort has gone into the modeling and simulation of adaptation in spiking neural networks (SNNs). Limitations in computational power imposed by network topology, however, constrain learning capabilities through connection weight modification alone. Constructive algorithms produce new neurons and connections, allowing automatic structural responses for applications of unknown complexity and nonstationary solutions. A conceptual analogy is developed and extended to theoretical conditions for modeling synaptic plasticity as network construction. Generalizing past constructive algorithms, we propose a framework for the design of novel constructive SNNs and demonstrate its application in the development of simulations for the validation of developed theory. Potential directions of future research and applications of STDC for biological modeling and machine learning are also discussed.

Modeling the insect mushroom bodies: application to a delayed match-to-sample task

Despite their small brains, insects show advanced capabilities in learning and task solving. Flies, honeybees and ants are becoming a reference point in neuroscience and a main source of inspiration for autonomous robot design issues and control algorithms. In particular, honeybees demonstrate to be able to autonomously abstract complex associations and apply them in tasks involving different sensory modalities within the insect brain. Mushroom Bodies (MBs) are worthy of primary attention for understanding memory and learning functions in insects. In fact, even if their main role regards olfactory conditioning, they are involved in many behavioral achievements and learning capabilities, as has been shown in honeybees and flies. Owing to the many neurogenetic tools, the fruit fly Drosophila became a source of information for the neuroarchitecture and biochemistry of the MBs, although the MBs of flies are by far simpler in organization than their honeybee orthologs. Electrophysiological studies, in turn, became available on the MBs of locusts and honeybees. In this paper a novel bio-inspired neural architecture is presented, which represents a generalized insect MB with the basic features taken from fruit fly neuroanatomy. By mimicking a number of different MB functions and architecture, we can replace and improve formerly used artificial neural networks. The model is a multi-layer spiking neural network where key elements of the insect brain, the antennal lobes, the lateral horn region, the MBs, and their mutual interactions are modeled. In particular, the model is based on the role of parts of the MBs named MB-lobes, where interesting processing mechanisms arise on the basis of spatio-temporal pattern formation. The introduced network is able to model learning mechanisms like olfactory conditioning seen in honeybees and flies and was found able also to perform more complex and abstract associations, like the delayed matching-to-sample tasks known only from honeybees. A biological basis of the proposed model is presented together with a detailed description of the architecture. Simulation results and remarks on the biological counterpart are also reported to demonstrate the possible applications of the designed computational model. Such neural architecture, able to autonomously learn complex associations is envisaged to be a suitable basis for an immediate implementation within an robot control architecture.

HARDWARE IMPLEMENTATION OF STOCHASTIC SPIKING NEURAL NETWORKS

Spiking Neural Networks, the last generation of Artificial Neural Networks, are characterized by its bio-inspired nature and by a higher computational capacity with respect to other neural models. In real biological neurons, stochastic processes represent an important mechanism of neural behavior and are responsible of its special arithmetic capabilities. In this work we present a simple hardware implementation of spiking neurons that considers this probabilistic nature. The advantage of the proposed implementation is that it is fully digital and therefore can be massively implemented in Field Programmable Gate Arrays. The high computational capabilities of the proposed model are demonstrated by the study of both feed-forward and recurrent networks that are able to implement high-speed signal filtering and to solve complex systems of linear equations.

Mobility timing for agent communities, a cue for advanced connectionist systems

We introduce a wait-and-chase scheme that models the contact times between moving agents within a connectionist construct. The idea that elementary processors move within a network to get a proper position is borne out both by biological neurons in the brain morphogenesis and by agents within social networks. From the former, we take inspiration to devise a medium-term project for new artificial neural network training procedures where mobile neurons exchange data only when they are close to one another in a proper space (are in contact). From the latter, we accumulate mobility tracks experience. We focus on the preliminary step of characterizing the elapsed time between neuron contacts, which results from a spatial process fitting in the family of random processes with memory, where chasing neurons are stochastically driven by the goal of hitting target neurons. Thus, we add an unprecedented mobility model to the literature in the field, introducing a distribution law of the intercontact times that merges features of both negative exponential and Pareto distribution laws. We give a constructive description and implementation of our model, as well as a short analytical form whose parameters are suitably estimated in terms of confidence intervals from experimental data. Numerical experiments show the model and related inference tools to be sufficiently robust to cope with two main requisites for its exploitation in a neural network: the nonindependence of the observed intercontact times and the feasibility of the model inversion problem to infer suitable mobility parameters.

Multiagent reinforcement learning: spiking and nonspiking agents in the iterated Prisoner's Dilemma

This paper investigates multiagent reinforcement learning (MARL) in a general-sum game where the payoffs' structure is such that the agents are required to exploit each other in a way that benefits all agents. The contradictory nature of these games makes their study in multiagent systems quite challenging. In particular, we investigate MARL with spiking and nonspiking agents in the Iterated Prisoner's Dilemma by exploring the conditions required to enhance its cooperative outcome. The spiking agents are neural networks with leaky integrate-and-fire neurons trained with two different learning algorithms: 1) reinforcement of stochastic synaptic transmission, or 2) reward-modulated spike-timing-dependent plasticity with eligibility trace. The nonspiking agents use a tabular representation and are trained with Q- and SARSA learning algorithms, with a novel reward transformation process also being applied to the Q-learning agents. According to the results, the cooperative outcome is enhanced by: 1) transformed internal reinforcement signals and a combination of a high learning rate and a low discount factor with an appropriate exploration schedule in the case of non-spiking agents, and 2) having longer eligibility trace time constant in the case of spiking agents. Moreover, it is shown that spiking and nonspiking agents have similar behavior and therefore they can equally well be used in a multiagent interaction setting. For training the spiking agents in the case where more than one output neuron competes for reinforcement, a novel and necessary modification that enhances competition is applied to the two learning algorithms utilized, in order to avoid a possible synaptic saturation. This is done by administering to the networks additional global reinforcement signals for every spike of the output neurons that were not "responsible" for the preceding decision.

Optimization methods for spiking neurons and networks

Spiking neurons and spiking neural circuits are finding uses in a multitude of tasks such as robotic locomotion control, neuroprosthetics, visual sensory processing, and audition. The desired neural output is achieved through the use of complex neuron models, or by combining multiple simple neurons into a network. In either case, a means for configuring the neuron or neural circuit is required. Manual manipulation of parameters is both time consuming and non-intuitive due to the nonlinear relationship between parameters and the neuron's output. The complexity rises even further as the neurons are networked and the systems often become mathematically intractable. In large circuits, the desired behavior and timing of action potential trains may be known but the timing of the individual action potentials is unknown and unimportant, whereas in single neuron systems the timing of individual action potentials is critical. In this paper, we automate the process of finding parameters. To configure a single neuron we derive a maximum likelihood method for configuring a neuron model, specifically the Mihalas-Niebur Neuron. Similarly, to configure neural circuits, we show how we use genetic algorithms (GAs) to configure parameters for a network of simple integrate and fire with adaptation neurons. The GA approach is demonstrated both in software simulation and hardware implementation on a reconfigurable custom very large scale integration chip.

A spiking neural network model of the medial superior olive using spike timing dependent plasticity for sound localization

Sound localization can be defined as the ability to identify the position of an input sound source and is considered a powerful aspect of mammalian perception. For low frequency sounds, i.e., in the range 270 Hz–1.5 KHz, the mammalian auditory pathway achieves this by extracting the Interaural Time Difference between sound signals being received by the left and right ear. This processing is performed in a region of the brain known as the Medial Superior Olive (MSO). This paper presents a Spiking Neural Network (SNN) based model of the MSO. The network model is trained using the Spike Timing Dependent Plasticity learning rule using experimentally observed Head Related Transfer Function data in an adult domestic cat. The results presented demonstrate how the proposed SNN model is able to perform sound localization with an accuracy of 91.82% when an error tolerance of ±10° is used. For angular resolutions down to 2.5°, it will be demonstrated how software based simulations of the model incur significant computation times. The paper thus also addresses preliminary implementation on a Field Programmable Gate Array based hardware platform to accelerate system performance.

Cellular Nonlinear Networks for the emergence of perceptual states: application to robot navigation control

In this paper a new general purpose perceptual control architecture, based on nonlinear neural lattices, is presented and applied to solve robot navigation tasks. Insects show the ability to react to certain stimuli with simple reflexes, using direct sensory-motor pathways, which can be considered as basic behaviors, inherited and pre-wired. Relevant brain centres, known as Mushroom Bodies (MB) and Central Complex (CX) were recently identified in insects: though their functional details are not yet fully understood, it is known that they provide secondary pathways allowing the emergence of cognitive behaviors. These are gained through the coordination of the basic abilities to satisfy the insect's needs. Taking inspiration from this evidence, our architecture modulates, through a reinforcement learning, a set of competitive and concurrent basic behaviors in order to accomplish the task assigned through a reward function. The core of the architecture is constituted by the so-called Representation layer, used to create a concise picture of the current environment situation, fusing together different stimuli for the emergence of perceptual states. These perceptual states are steady state solutions of lattices of Reaction-Diffusion Cellular Nonlinear Networks (RD-CNN), designed to show Turing patterns. The exploitation of the dynamics of the multiple equilibria of the network is emphasized through the adaptive shaping of the basins of attraction for each emerged pattern. New experimental campaigns on standard robotic platforms are reported to demonstrate the potentiality and the effectiveness of the approach.

An incomplete gallery: machines, cognition, and nonlinearities

In this communication, some issues related to the old but still open question, on how far the development of cognitive processing in artificial machines can go, are discussed. A selected gallery of images derived from laboratory experiments are presented. The incompleteness of the gallery is as that in the definition of what we mean as cognitive processing.