Search Results for author:
Found 28 papers, 19 papers with code
SpikingJelly: An open-source machine learning infrastructure platform for spike-based intelligence
Spiking neural networks (SNNs) aim to realize brain-inspired intelligence on neuromorphic chips with high energy efficiency by introducing neural dynamics and spike properties.
Audio classification with Dilated Convolution with Learnable Spacings
Dilated convolution with learnable spacings (DCLS) is a recent convolution method in which the positions of the kernel elements are learned throughout training by backpropagation.
Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
In SNNs, delays refer to the time needed for one spike to travel from one neuron to another.
Ranked #1 on
Audio Classification
on SSC
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation
Dilated Convolution with Learnable Spacings (DCLS) is a recently proposed variation of the dilated convolution in which the spacings between the non-zero elements in the kernel, or equivalently their positions, are learnable.
Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies
Vanilla spiking neurons in Spiking Neural Networks (SNNs) use charge-fire-reset neuronal dynamics, which can only be simulated serially and can hardly learn long-time dependencies.
Optical flow estimation from event-based cameras and spiking neural networks
Event-based sensors are an excellent fit for Spiking Neural Networks (SNNs), since the coupling of an asynchronous sensor with neuromorphic hardware can yield real-time systems with minimal power requirements.
Drastically Reducing the Number of Trainable Parameters in Deep CNNs by Inter-layer Kernel-sharing
However, most SOTA networks are too large for edge computing.
Dilated convolution with learnable spacings
We call this method "Dilated Convolution with Learnable Spacings" (DCLS) and generalize it to the n-dimensional convolution case.
StereoSpike: Depth Learning with a Spiking Neural Network
Here we solved it using an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Network (SNN) with a slightly modified U-Net-like encoder-decoder architecture, that we named StereoSpike.
Spiking neural networks trained via proxy
By assuming IF neuron with rate-coding as an approximation of ReLU, we backpropagate the error of the SNN in the proxy ANN to update the shared weights, simply by replacing the ANN final output with that of the SNN.
Spike time displacement based error backpropagation in convolutional spiking neural networks
To do so, we consider a convolutional SNN (CSNN) with two sets of weights: real-valued weights that are updated in the backward pass and their signs, binary weights, that are employed in the feedforward process.
Ranked #11 on
Image Classification
on Fashion-MNIST
Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning
Multi-label audio tagging consists of assigning sets of tags to audio recordings.
Deep Residual Learning in Spiking Neural Networks
Previous Spiking ResNet mimics the standard residual block in ANNs and simply replaces ReLU activation layers with spiking neurons, which suffers the degradation problem and can hardly implement residual learning.
Encrypted Internet traffic classification using a supervised Spiking Neural Network
Internet traffic recognition is an essential tool for access providers since recognizing traffic categories related to different data packets transmitted on a network help them define adapted priorities.
Low-activity supervised convolutional spiking neural networks applied to speech commands recognition
Deep Neural Networks (DNNs) are the current state-of-the-art models in many speech related tasks.
BS4NN: Binarized Spiking Neural Networks with Temporal Coding and Learning
We recently proposed the S4NN algorithm, essentially an adaptation of backpropagation to multilayer spiking neural networks that use simple non-leaky integrate-and-fire neurons and a form of temporal coding known as time-to-first-spike coding.
Technical report: supervised training of convolutional spiking neural networks with PyTorch
Indeed, the most commonly used spiking neuron model, the leaky integrate-and-fire neuron, obeys a differential equation which can be approximated using discrete time steps, leading to a recurrent relation for the potential.
S4NN: temporal backpropagation for spiking neural networks with one spike per neuron
In particular, in the readout layer, the first neuron to fire determines the class of the stimulus.
SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
Application of deep convolutional spiking neural networks (SNNs) to artificial intelligence (AI) tasks has recently gained a lot of interest since SNNs are hardware-friendly and energy-efficient.
Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
We trained it using a combination of spike-timing-dependent plasticity (STDP) for the lower layers and reward-modulated STDP (R-STDP) for the higher ones.
Optimal localist and distributed coding of spatiotemporal spike patterns through STDP and coincidence detection
Here we investigated how a single spiking neuron can optimally respond to one given pattern (localist coding), or to either one of several patterns (distributed coding, i. e. the neuron's response is ambiguous but the identity of the pattern could be inferred from the response of multiple neurons), but not to random inputs.
First-spike based visual categorization using reward-modulated STDP
In the highest layers, each neuron was assigned to an object category, and it was assumed that the stimulus category was the category of the first neuron to fire.
Object categorization in finer levels requires higher spatial frequencies, and therefore takes longer
This means that, low frequency information is sufficient for superordinate level, but not for the basic and subordinate levels.
STDP-based spiking deep convolutional neural networks for object recognition
Coding was very sparse, with only a few thousands spikes per image, and in some cases the object category could be reasonably well inferred from the activity of a single higher-order neuron.
STDP allows close-to-optimal spatiotemporal spike pattern detection by single coincidence detector neurons
Our results indicate that a relatively small $\tau$ (at most a few tens of ms) is usually optimal, even when the pattern is much longer.
Humans and deep networks largely agree on which kinds of variation make object recognition harder
This feed-forward architecture has inspired a new generation of bio-inspired computer vision systems called deep convolutional neural networks (DCNN), which are currently the best algorithms for object recognition in natural images.
Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition
Deep convolutional neural networks (DCNNs) have attracted much attention recently, and have shown to be able to recognize thousands of object categories in natural image databases.
Bio-inspired Unsupervised Learning of Visual Features Leads to Robust Invariant Object Recognition
Retinal image of surrounding objects varies tremendously due to the changes in position, size, pose, illumination condition, background context, occlusion, noise, and nonrigid deformations.
