arXiv subjects

Mathias Quoy

Publications and source records attributed to Mathias Quoy.

13 recordsLinked to original sources

arXiv2026

Structure from rank: Rank-order coding as a bridge from sequence to structure

Understanding how structured sequence information can be represented and generalized in neural systems is key to modeling the transition from acoustic input to emergent structure. In this study, we propose a rank-order based neural network inspired by the STG-LIFG-PMC pathway, modeling the bottom-up transition from acoustic input to abstract rank representation and the top-down generation from that representation to motor execution. Building on previous work in rank coding, we first demonstrate that this model efficiently compresses input while retaining the capacity to reconstruct full utterances from partial cues, revealing emergent structure-sensitive generation process that reflects context-general representations of sensorimotor states, which are later shaped into context-specific motor plans during speech planning. We then show that the network exhibits global-level novelty detection similar to the P3B novelty wave, replicating the global-sequence-sensitive mechanism. As a supplement, we also compare the model's behavior under local (index-level) and global (rank-level) perturbations, revealing robustness to superficial variation and sensitivity to abstract structural violation, key features associated with hierarchical generalization. These results suggest that rank-order coding not only serves as a compact encoding scheme but also captures hierarchical structure in acoustic sequences.

cs.NE↗

arXiv2025

CERNet: Class-Embedding Predictive-Coding RNN for Unified Robot Motion, Recognition, and Confidence Estimation

Robots interacting with humans must not only generate learned movements in real-time, but also infer the intent behind observed behaviors and estimate the confidence of their own inferences. This paper proposes a unified model that achieves all three capabilities within a single hierarchical predictive-coding recurrent neural network (PC-RNN) equipped with a class embedding vector, CERNet, which leverages a dynamically updated class embedding vector to unify motor generation and recognition. The model operates in two modes: generation and inference. In the generation mode, the class embedding constrains the hidden state dynamics to a class-specific subspace; in the inference mode, it is optimized online to minimize prediction error, enabling real-time recognition. Validated on a humanoid robot across 26 kinesthetically taught alphabets, our hierarchical model achieves 76% lower trajectory reproduction error than a parameter-matched single-layer baseline, maintains motion fidelity under external perturbations, and infers the demonstrated trajectory class online with 68% Top-1 and 81% Top-2 accuracy. Furthermore, internal prediction errors naturally reflect the model's confidence in its recognition. This integration of robust generation, real-time recognition, and intrinsic uncertainty estimation within a compact PC-RNN framework offers a compact and extensible approach to motor memory in physical robots, with potential applications in intent-sensitive human-robot collaboration.

cs.RO↗

arXiv2025

Confidence-Based Self-Training for EMG-to-Speech: Leveraging Synthetic EMG for Robust Modeling

Voiced Electromyography (EMG)-to-Speech (V-ETS) models reconstruct speech from muscle activity signals, facilitating applications such as neurolaryngologic diagnostics. Despite its potential, the advancement of V-ETS is hindered by a scarcity of paired EMG-speech data. To address this, we propose a novel Confidence-based Multi-Speaker Self-training (CoM2S) approach, along with a newly curated Libri-EMG dataset. This approach leverages synthetic EMG data generated by a pre-trained model, followed by a proposed filtering mechanism based on phoneme-level confidence to enhance the ETS model through the proposed self-training techniques. Experiments demonstrate our method improves phoneme accuracy, reduces phonological confusion, and lowers word error rate, confirming the effectiveness of our CoM2S approach for V-ETS. In support of future research, we will release the codes and the proposed Libri-EMG dataset-an open-access, time-aligned, multi-speaker voiced EMG and speech recordings.

cs.SD↗

arXiv2024

Developmental Predictive Coding Model for Early Infancy Mono and Bilingual Vocal Continual Learning

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-sized generative neural network equipped with a continual learning mechanism based on predictive coding for mono-and bilingual speech sound learning (referred to as language sound acquisition during ''critical period'') and a compositional optimization mechanism for generation where no learning is involved (later infancy sound imitation). Our model prioritizes interpretability and demonstrates the advantages of online learning: Unlike deep networks requiring substantial offline training, our model continuously updates with new data, making it adaptable and responsive to changing inputs. Through experiments, we demonstrate that if second language acquisition occurs during later infancy, the challenges associated with learning a foreign language after the critical period amplify, replicating the perceptual narrowing effect.

cs.AI↗

arXiv2024

Emergence and maintenance of modularity in neural networks with Hebbian and anti-Hebbian inhibitory STDP

The modular and hierarchical organization of the brain is believed to support the coexistence of segregated (specialization) and integrated (binding) information processes. A relevant question is yet to understand how such architecture naturally emerges and is sustained over time, given the plastic nature of the brain's wiring. Following evidences that the sensory cortices organize into assemblies under selective stimuli, it has been shown that stable neuronal assemblies can emerge due to targeted stimulation, embedding various forms of synaptic plasticity in presence of homeostatic and/or control mechanisms. Here, we show that simple spike-timing-dependent plasticity (STDP) rules, based only on pre- and post-synaptic spike times, can also lead to the stable encoding of memories in the absence of any control mechanism. We develop a model of spiking neurons, trained by stimuli targeting different subpopulations. The model satisfies some biologically plausible features: (i) it contains excitatory and inhibitory neurons with Hebbian and anti-Hebbian STDP; (ii) neither the neuronal activity nor the synaptic weights are frozen after the learning phase. Instead, the neurons are allowed to fire spontaneously while synaptic plasticity remains active. We find that only the combination of two inhibitory STDP subpopulations allows for the formation of stable modules in the network, with each subpopulation playing a distinctive role. The Hebbian subpopulation controls for the firing activity, while the anti-Hebbian neurons promote pattern selectivity. After the learning phase, the network settles into an asynchronous irregular resting-state. This post-learning activity is associated with spontaneous memory recalls which turn out to be fundamental for the long-term consolidation of the learned memories.

q-bio.NC↗

arXiv2023

Networks' modulation: How different structural network properties affect the global synchronization of coupled Kuramoto oscillators

In a large variety of systems (biological, physical, social etc.), synchronization occurs when different oscillating objects tune their rhythm when they interact with each other. The different underlying network defining the connectivity properties among these objects drives the global dynamics in a complex fashion and affects the global degree of synchrony of the system. Here we study the impact of such types of different network architectures, such as Fully-Connected, Random, Regular ring lattice graph, Small-World and Scale-Free in the global dynamical activity of a system of coupled Kuramoto phase oscillators. We fix the external stimulation parameters and we measure the global degree of synchrony when different fractions of nodes receive stimulus. These nodes are chosen either randomly or based on their respective strong/weak connectivity properties (centrality, shortest path length and clustering coefficient). Our main finding is, that in Scale-Free and Random networks a sophisticated choice of nodes based on their eigenvector centrality and average shortest path length exhibits a systematic trend in achieving higher degree of synchrony. However, this trend does not occur when using the clustering coefficient as a criterion. For the other types of graphs considered, the choice of the stimulated nodes (randomly vs selectively using the aforementioned criteria) does not seem to have a noticeable effect.

nlin.AO↗

arXiv2022

On the Relationship Between Variational Inference and Auto-Associative Memory

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 previously stored representations. We then study how different neural network approaches to variational inference can be applied in this framework. We compare methods relying on amortized inference such as Variational Auto Encoders and methods relying on iterative inference such as Predictive Coding and suggest combining both approaches to design new auto-associative memory models. We evaluate the obtained algorithms on the CIFAR10 and CLEVR image datasets and compare them with other associative memory models such as Hopfield Networks, End-to-End Memory Networks and Neural Turing Machines.

cs.LG↗

arXiv2021

A Predictive Coding Account for Chaotic Itinerancy

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 trajectories similar to chaotic itinerancy in the presence of input noise. We propose two scenarios generating random and past-independent attractor switching trajectories using our model.

cs.NE↗

arXiv2021

Bidirectional Interaction between Visual and Motor Generative Models using Predictive Coding and Active Inference

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 of motor trajectories. We furthermore inquire the effects of bidirectional interactions between the motor and the visual modules. The architecture is tested on the control of a simulated robotic arm learning to reproduce handwritten letters.

cs.AI↗

arXiv2020

Towards a Neural Model for Serial Order in Frontal Cortex: a Brain Theory from Memory Development to Higher-Level Cognition

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) use its primary functionality of detecting hierarchical patterns in temporal signals as a second purpose to organize the spatial ordering of the cortical networks in the developing brain itself. Our hypothesis is that the PFC detects the hierarchical structure in temporal sequences in the form of ordinal patterns and use them to index information hierarchically in different parts of the brain. Henceforth, we propose that this mechanism for detecting patterns participates in the ordinal organization development of the brain itself; i.e., the bootstrapping of the connectome. By doing so, it gives the tools to the language-ready brain for manipulating abstract knowledge and planning temporally ordered information; i.e., the emergence of symbolic thinking and language. We will review neural models that can support such mechanisms and propose new ones. We will confront then our ideas with evidence from developmental, behavioral and brain results and make some hypotheses, for instance, on the construction of the mirror neuron system, on embodied cognition, and on the capacity of learning-to-learn.

cs.NE↗

arXiv2020

Autonomous learning and chaining of motor primitives using the Free Energy Principle

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 trajectories. To evaluate the repertoires built with our method, we exploit them in a handwriting task where primitives are chained to produce long-range sequences.

cs.NE↗

arXiv2008

A mathematical analysis of the effects of Hebbian learning rules on the dynamics and structure of discrete-time random recurrent neural networks

We present a mathematical analysis of the effects of Hebbian learning in random recurrent neural networks, with a generic Hebbian learning rule including passive forgetting and different time scales for neuronal activity and learning dynamics. Previous numerical works have reported that Hebbian learning drives the system from chaos to a steady state through a sequence of bifurcations. Here, we interpret these results mathematically and show that these effects, involving a complex coupling between neuronal dynamics and synaptic graph structure, can be analyzed using Jacobian matrices, which introduce both a structural and a dynamical point of view on the neural network evolution. Furthermore, we show that the sensitivity to a learned pattern is maximal when the largest Lyapunov exponent is close to 0. We discuss how neural networks may take advantage of this regime of high functional interest.

nlin.CD↗

arXiv2007

Effects of Hebbian learning on the dynamics and structure of random networks with inhibitory and excitatory neurons

The aim of the present paper is to study the effects of Hebbian learning in random recurrent neural networks with biological connectivity, i.e. sparse connections and separate populations of excitatory and inhibitory neurons. We furthermore consider that the neuron dynamics may occur at a (shorter) time scale than synaptic plasticity and consider the possibility of learning rules with passive forgetting. We show that the application of such Hebbian learning leads to drastic changes in the network dynamics and structure. In particular, the learning rule contracts the norm of the weight matrix and yields a rapid decay of the dynamics complexity and entropy. In other words, the network is rewired by Hebbian learning into a new synaptic structure that emerges with learning on the basis of the correlations that progressively build up between neurons. We also observe that, within this emerging structure, the strongest synapses organize as a small-world network. The second effect of the decay of the weight matrix spectral radius consists in a rapid contraction of the spectral radius of the Jacobian matrix. This drives the system through the ``edge of chaos'' where sensitivity to the input pattern is maximal. Taken together, this scenario is remarkably predicted by theoretical arguments derived from dynamical systems and graph theory.

q-bio.NC↗