Search Results for author:
Found 21 papers, 6 papers with code
Expanding memory in recurrent spiking networks
Recurrent spiking neural networks (RSNNs) are notoriously difficult to train because of the vanishing gradient problem that is enhanced by the binary nature of the spikes.
Stabilizing RNN Gradients through Pre-training
However, analysing deep recurrent networks, we identify a new additive source of exponential explosion that emerges from counting gradient paths in a rectangular grid in depth and time.
Excitatory/Inhibitory Balance Emerges as a Key Factor for RBN Performance, Overriding Attractor Dynamics
Reservoir computing provides a time and cost-efficient alternative to traditional learning methods. Critical regimes, known as the "edge of chaos," have been found to optimize computational performance in binary neural networks.
Efficient spike encoding algorithms for neuromorphic speech recognition
Finally, we show that several encoding methods result in improved performance over the conventional deep learning baseline in certain cases, further demonstrating the power of spike encoding algorithms in the encoding of real-valued signals and that neuromorphic implementation has the potential to outperform state of the art techniques.
Voltage-Dependent Synaptic Plasticity (VDSP): Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential
To validate the system-level performance of VDSP, we train a single-layer spiking neural network (SNN) for the recognition of handwritten digits.
Stabilizing Spiking Neuron Training
We show how it can be used to reduce the need of extensive grid-search of dampening, sharpness and tail-fatness of the SG.
Adaptive Approach For Sparse Representations Using The Locally Competitive Algorithm For Audio
An oriented grid search optimization was applied to adapt the gammachirp's parameters and improve the Matching Pursuit (MP) algorithm's sparsity along with the reconstruction quality.
Multi-level Attention Fusion Network for Audio-visual Event Recognition
Event classification is inherently sequential and multimodal.
NAAQA: A Neural Architecture for Acoustic Question Answering
We also test the addition of a MALiMo module in our model on both CLEAR2 and DAQA.
Signals to Spikes for Neuromorphic Regulated Reservoir Computing and EMG Hand Gesture Recognition
Using a simple machine learning algorithm after spike encoding, we report performance higher than the state-of-the-art spiking neural networks on two open-source datasets for hand gesture recognition.
AriEL: Volume Coding for Sentence Generation Comparisons
Then, we benchmark on a real dataset of human dialogues.
AVECL-UMONS database for audio-visual event classification and localization
We introduce the AVECL-UMons dataset for audio-visual event classification and localization in the context of office environments.
P-CRITICAL: A Reservoir Autoregulation Plasticity Rule for Neuromorphic Hardware
Backpropagation algorithms on recurrent artificial neural networks require an unfolding of accumulated states over time.
AriEL: volume coding for sentence generation
This partially supports to the hypothesis that encoding information into volumes instead of into points, can lead to improved retrieval of learned information with random sampling.
Language coverage and generalization in RNN-based continuous sentence embeddings for interacting agents
While it is known that those embeddings are able to learn some structures of language (e. g. grammar) in a purely data-driven manner, there is very little work on the objective evaluation of their ability to cover the whole language space and to generalize to sentences outside the language bias of the training data.
From Visual to Acoustic Question Answering
The AQA task consists of analyzing an acoustic scene composed by a combination of elementary sounds and answering questions that relate the position and properties of these sounds.
CLEAR: A Dataset for Compositional Language and Elementary Acoustic Reasoning
We introduce the task of acoustic question answering (AQA) in the area of acoustic reasoning.
Classification of auditory stimuli from EEG signals with a regulated recurrent neural network reservoir
The use of electroencephalogram (EEG) as the main input signal in brain-machine interfaces has been widely proposed due to the non-invasive nature of the EEG.
HoME: a Household Multimodal Environment
We introduce HoME: a Household Multimodal Environment for artificial agents to learn from vision, audio, semantics, physics, and interaction with objects and other agents, all within a realistic context.
Moving Toward High Precision Dynamical Modelling in Hidden Markov Models
In this paper, we propose that finely-tuned HMM topologies are essential for precise temporal modelling and that this approach should be investigated in state-of-the-art HMM system.
Regulation toward Self-organized Criticality in a Recurrent Spiking Neural Reservoir
This is due to the extremely non-linear dynamics of recurrent spiking neural networks.
