Alexandre Pitti

Verified

Alexandre verified their affiliation via an institutional email.

Learn more

Verified

Alexandre verified their affiliation via an institutional email.

Learn more

• PhD
• Professor (Full) at École Nationale Supérieure de l'Électronique et de ses Applications

Understanding how infants perceive speech sounds and language structures is still an open problem. Previous research in artificial neural networks has mainly focused on large dataset-dependent generative models, aiming to replicate language-related phenomena such as ''perceptual narrowing''. In this paper, we propose a novel approach using a small-...

Understanding how infants perceive speech sounds and language structures is still an open problem. Previous research in artificial neural networks has mainly focused on large dataset-dependent generative models, aiming to replicate language-related phenomena such as "perceptual narrowing". In this paper, we propose a novel approach using a small-si...

A social individual needs to effectively manage the amount of complex information in his or her environment relative to his or her own purpose to obtain relevant information. This paper presents a neural architecture aiming to reproduce attention mechanisms (alerting/orienting/selecting) that are efficient in humans during audiovisual tasks in robo...

The body morphology plays an important role in the way information is perceived and processed by an agent. We address an information theory (IT) account on how the precision of sensors, the accuracy of motors, their placement, the body geometry, shape the information structure in robots and computational codes. As an original idea, we envision the...

In this article, we propose a variational inference formulation of auto-associative memories, allowing us to combine perceptual inference and memory retrieval into the same mathematical framework. In this formulation, the prior probability distribution onto latent representations is made memory dependent, thus pulling the inference process towards...

This article presents a novel artificial skin technology based on the Electric Impedance Tomography (EIT) that employs multi-frequency currents for detecting the material and the temperature of objects in contact with piezoresistive sheets. To date, few artificial skins in the literature are capable of detecting an object’s material, e.g., wood, sk...

In this article, we propose a variational inference formulation of auto-associative memories, allowing us to combine perceptual inference and memory retrieval into the same mathematical framework. In this formulation, the prior probability distribution onto latent representations is made memory dependent, thus pulling the inference process towards...

Reaching and grasping objects in 3D is still a challenging task in robotics because they have to be done in an integrated fashion, as it is for tool-use or during imitation with a human partner. The visuo-motor networks in the human brain exploit a neural mechanism known as gain-field modulation to adapt different circuits together with respect to...

We propose that coding and decoding in the brain are achieved through digital computation using three principles: relative ordinal coding of inputs, random connections between neurons, and belief voting. Due to randomization and despite the coarseness of the relative codes, we show that these principles are sufficient for coding and decoding sequen...

In order to keep trace of information and grow up, the infant brain has to resolve the problem about where old information is located and how to index new ones. We propose that the immature prefrontal cortex (PFC) uses its primary functionality of detecting hierarchical patterns in temporal signals as a second feature to organize the spatial orderi...

Recurrent neural networks (RNNs) have been proved very successful at modeling sequential data such as language or motions. However, these successes rely on the use of the backpropagation through time (BPTT) algorithm, batch training, and the hypothesis that all the training data are available at the same time. In contrast, the field of developmenta...

As a phenomenon in dynamical systems allowing autonomous switching between stable behaviors, chaotic itinerancy has gained interest in neurorobotics research. In this study, we draw a connection between this phenomenon and the predictive coding theory by showing how a recurrent neural network implementing predictive coding can generate neural traje...

In this work, we build upon the Active Inference (AIF) and Predictive Coding (PC) frameworks to propose a neural architecture comprising a generative model for sensory prediction, and a distinct generative model for motor trajectories. We highlight how sequences of sensory predictions can act as rails guiding learning, control and online adaptation...

As a phenomenon in dynamical systems allowing autonomous switching between stable behaviors, chaotic itinerancy has gained interest in neurorobotics research. In this study, we draw a connection between this phenomenon and the predictive coding theory by showing how a recurrent neural network implementing predictive coding can generate neural traje...

In this work, we build upon the Active Inference (AIF) and Predictive Coding (PC) frameworks to propose a neural architecture comprising a generative model for sensory prediction, and a distinct generative model for motor trajectories. We highlight how sequences of sensory predictions can act as rails guiding learning, control and online adaptation...

We propose a developmental model inspired by the cortico-basal system (CX-BG) for vocal learning in babies and for solving the correspondence mismatch problem they face when they hear unfamiliar voices, with different tones and pitches. This model is based on the neural architecture INFERNO standing for Iterative Free-Energy Optimization of Recurre...

Electrical Impedance Tomography (EIT) is an imaging technique used recently as a tactile sensor. The ad- vantages are the absence of electrodes within the sensor area, low-cost design and material. Moreover, it also includes low electric consumption and it can be shaped freely. Although EIT reconstruction gives a low spatial resolution, the retriev...

In order to keep trace of information, the brain has to resolve the problem where information is and how to index new ones. We propose that the neural mechanism used by the prefrontal cortex (PFC) to detect structure in temporal sequences, based on the temporal order of incoming information, has served as second purpose to the spatial ordering and...

In this article, we apply the Free-Energy Principle to the question of motor primitives learning. An echo-state network is used to generate motor trajectories. We combine this network with a perception module and a controller that can influence its dynamics. This new compound network permits the autonomous learning of a repertoire of motor trajecto...

Starting from biological systems, we review the interest of active perception for object recognition in an autonomous system. Foveated vision and control of the eye saccade introduce strong benefits related to the differentiation of a ‘what’ pathway recognizing some local parts in the image and a ‘where’ pathway related to moving the fovea in that...

We present a framework based on iterative free-energy optimization with spiking neural networks for modeling the fronto-striatal system (PFC-BG) for the generation and recall of audio memory sequences. In line with neuroimaging studies carried out in the PFC, we propose a genuine coding strategy using the gain-modulation mechanism to represent abst...

Adults readily make associations between stimuli perceived consecutively through different sense modalities, such as shapes and sounds. Researchers have only recently begun to investigate such correspondences in infants but only a handful of studies have focused on infants less than a year old. Are infants able to make cross-sensory correspondences...

Representing objects in space is difficult because sensorimotor events are anchored in different reference frames, which can be either eye-, arm-, or target-centered. In the brain, Gain-Field (GF) neurons in the parietal cortex are involved in computing the necessary spatial transformations for aligning the tactile, visual and proprioceptive signal...

Intelligent tutoring systems are increasingly effective for helping the teacher's work with children. However, these technologies are still poorly used for cognitively impaired infants who display autistic spectrum disorders and intellectual disabilities as they don't adapt easily to each infant. We propose an adaptive learning system called SPEAKY...

Perceiving our own body posture improves the way we move dynamically and reversely, motion coordination serves to learn better the position of our own body. Following this idea, we present a neural architecture toward reaching movements and body self-perception from a developmental perspective. Our framework is based on the neurobiological mechanis...

We present a neuronal architecture to control a compliant robotic model of the human vertebral column for postural balance. The robotic structure is designed using the principle of tensegrity that ensures to be lightweight, auto-replicative with multi-degrees of freedom, flexible and also robust to perturbations. We model the central pattern genera...

Advances in Artificial Intelligence and robotics are currently questioning theethical framework of their applications to deal with potential drifts, as well as the way inwhich these algorithms learn because they will have a strong impact on the behavior ofrobots and the type of robots. interactions with people. We would like to highlight someprinci...

We present a neural architecture capable to control synergistically a flexible robotic model of the human vertebral column toward balance and upward posture. The neural controller is composed of non-linear oscillators that control each vertebrae of the column constructed on the principle of tensegrity. They play the role of the central pattern gene...

Advances in Artificial Intelligence and robotics are currently questioning theethical framework of their applications to deal with potential drifts, as well as the way inwhich these algorithms learn because they will have a strong impact on the behavior ofrobots and the type of robots. interactions with people. We would like to highlight someprinci...

We propose to develop the notion of Alignment as one general design principle to understand how to model the Self. Alignment encompasses the notions of temporal contingency detection between sensors and motors to calibrate the self, the spatial alignment between sensors of different reference frames to represent the physical limits of the body for...

Human working memory is capable to generate dynamically robust and flexible neuronal sequences for action planning, problem solving and decision making. However, current neurocomputational models of working memory find hard to achieve these capabilities since intrinsic noise is difficult to stabilize over time and destroys global synchrony. As part...

The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework base...

Perceptual illusions across multiple modalities, such as the rubber-hand illusion, show how dynamic the brain is at adapting its body image and at determining what is part of it (the self) and what is not (others). Several research studies showed that redundancy and contingency among sensory signals are essential for perception of the illusion and...

This paper proposes a computational model for learning robot control and sequence planning based on the ideomotor principle. This model encodes covariation laws between sensors and motors in a modular fashion and exploits these primitive skills to build complex action sequences, potentially involving tool-use. Implemented for a robotic arm, the mod...

Touch perception is an important sense to model in humanoid robots to interact physically and socially with humans. We present a neural controller that can adapt the compliance of the robot arm in four directions using as input the tactile information from an artificial skin and as output the estimated torque for admittance control-loop reference....

The learning of sensorimotor primitives in an open-ended manner is important to achieve all the possible tasks a robot can do, even those never experienced before. In this short paper, we propose a neural architecture called Dynamic Sensorimotor Model (DSM) (1) that learn co-variation rules between sensors and motors for sensorimotor prediction, (2...

The question whether newborns possess inborn social skills is a long debate in developmental psychology. Fetal behavioral and anatomical observations show evidences for the control of eye movements and facial behaviors during the third trimester of pregnancy whereas specific sub-cortical areas, like the superior colliculus (SC) and the striatum app...

The sense of touch is considered as an essential feature for robots in order to improve the quality of their physical and social interactions. For instance, tactile devices have to be fast enough to interact in real time, robust against noise to process rough sensory information as well as adaptive to represent the structure and topography of a tac...

We explore different strategies to overcome the problem of sensorimotor transformation that babies face during development, especially in the case of tool-use. From a developmental perspective, we investigate a model based on absolute coordinate frames of reference, and another one based on relative coordinate frames of reference. In a situation of...

Abstract The so-called self-other correspondence problem in imitation demands to find the transformation that maps the motor dynamics of one partner to our owns. This requires a general purpose sensorimotor mechanism that transforms an external fixation-point (partner’s shoulder) reference frame to one’s own body-centred reference frame. We propose...

During development, infants learn to differentiate their motor behaviors relative to various contexts by exploring and identifying the correct structures of causes and effects that they can perform; these structures of actions are called task sets or internal models. The ability to detect the structure of new actions, to learn them and to select on...

We propose a developmental scenario for explaining neonatal imitation. We hypothesize that the early maturation of the superior colliculus (SC) at the fetal period may strongly contribute to the construction of the social brain. We underly two mechanisms in SC potentially important which are (1) spatial topological organization of the unisensory mo...

The question whether newborns possess inborn social skills is a long debate in developmental psychology. Fetal behavioral and anatomical observations show evidences for the control of eye movements and facial behaviors during the third trimester of pregnancy whereas specific sub-cortical areas, like the superior colliculus (SC) and the striatum app...

This paper proposes a low-cost system, based on the method of Electrical Impedance Tomography (EIT), for data acquisition from soft conductive fabric, for the purposes of designing of robots artificial skin. A simple multiplexer/ demultiplexer circuit is used for retrieving the resistance field from the pair-wised electrodes which inject the electr...

Newborns present impressive developmental changes during the first year in almost all domains marked by memory categorization and variability. We propose that one important actor of this developmental shift is the gradual influence of the cholinergic system in the cortico-hippocampal circuits. Based on neurological observations and developmental st...

En allant à rebours de l'approche " penser, c'est calculer ", qui a été l'axe principal de la recherche en intelligence artificielle jusque dans les années 1980, " La Révolution de l'intelligence du corps développe l'idée que l'intelligence a besoin d'un corps " pour interagir avec l'environnement, selon le contexte et l'instant. Cette proposition...

Seeing is not just done through the eyes, it involves the integration of other modalities such as auditory, proprioceptive and tactile information, to locate objects, persons and also the limbs. We hypothesize that the neural mechanism of gain-field modulation, which is found to process coordinate transform between modalities in the superior collic...

In this paper, we attempt to reconciliate two views of spatial development based on two mechanisms of statistical learning and of sensory alignment. Conflicting results in developmental psychology attribute either a developmental period to spatial cognition (Piaget). Besides, these results conflict with other researches in which infants do demonstr...

This chapter reviews several computational models of the ontogenetic and epigenetic mechanisms that contribute to the construction and to the functioning of the shared sensory-motor circuits in the parieto-motor cortex. The primary role of these shared circuits, which include the so-called mirror neurons system, is found to transform the sensorimot...

Infants present impressive developmental changes during the first year in almost all domains marked by memory categorization and variability. We propose that one important actor for this developmental shift is the cholinergic innervation of the cortico-hippocampal circuits. Based on neurological observations and developmental studies done in infant...

The motion behaviors of vertebrates require the correct coordination of the muscles and of the body limbs even for the most stereotyped ones like the rhythmical patterns. It means that the neural circuits have to share some part of the control with the material properties and the body morphology in order to rise any of these motor synergies. To thi...

Infants' ability to orient their actions in space improves dramatically after their sixth month when they start to plan the correct motion of their hands for reaching objects. Recent developmental studies speculate that this enhancement of spatial memory corre-sponds to the activation of the hippocam-pal system that shapes the parieto-motor cor-tic...

Pattern generators found in the spinal cord are no more seen as simple rhythmic oscillators for motion control. Indeed, they achieve flexible and dynamical coordination in interaction with the body and the environment dynamics giving to rise motor synergies. Discovering the mechanisms underlying the control of motor synergies constitutes an importa...

Agency is the sense that I am the cause or author of a movement. Babies develop early this feeling by perceiving the contingency between afferent (sensor) and efferent (motor) information. A comparator model is hypothesized to be associated with many brain regions to monitor and simulate the concordance between self-produced actions and their conse...

In this paper, we present a neural architecture aimed to reproduce the qualitative properties of the mirror neurons system which encodes neural representations of actions either performed or observed. Several biological researches have emphasized some of its important aspects, for instance, the tight coupling between perception and action, the cruc...

Embodied action representation and action understanding are the first steps to understand what it means to communicate. We present a biologically plausible mechanism to the representation and the recognition of actions in a neural network with spiking neurons based on the learning mechanism of spike-timing-dependent plasticity (STDP). We show how g...

Metastability is a property of systems composed of many interacting parts wherein the parts exhibit simultaneously a tendency to function autonomously (local segregation) and a tendency to cooperate (global integration). We study anisotropically coupled map lattices and discover that for specific values of the coupling control parameters the entire...

We present a neural architecture aimed to reproduce the qualitative properties of the mirror neurons system which encodes neural representations of actions either performed or observed. Several biological researches have emphasized some of its important aspects, for instance, the tight coupling between the sensorimotor maps, the crucial role of tim...

In the study of complex systems a fundamental issue is the mapping of the networks of interaction between constituent subsystems of a complex system or between multiple complex systems. Such networks define the web of dependencies and patterns of continuous and dynamic coupling between the system's elements characterized by directed flow of informa...

Self-exploration of movement possibilities and exploitation of natural dynamics are two crucial aspects of intelligent autonomous systems. We intro- duce a dynamical exploration strategy which combines chaotic neural activity with feedback-induced resonance. The underlying mechanism satisfies three conditions: (1) resonant patterns are discovered e...

We address the issue of how an embodied system can autonomously explore and discover the action possibilities inherent to its body. Our basic assumption is that the intrinsic dynamics of a system can be explored by perturbing the system through small but well-timed feedback actions and by exploiting a mechanism of feedback resonance. We hypothesize...

Synchronization is the dynamic adjustment of rhythms of oscillating systems. The ques-tion arises of whether the complex patterns emerging from the interaction of an embod-ied system's internal and external dynamics can be explained and quantified in terms of synchronization. Taking an information the-oretical stance, we make the assumption that sy...