Visual recognition is currently one of the most important and active research areas in computer vision, pattern recognition, and even the general field of artificial intelligence.
Although spiking neural networks (SNNs) take benefits from the bio-plausible neural modeling, the low accuracy under the common local synaptic plasticity learning rules limits their application in many practical tasks.
However, when aggregating individual events into frames with a new higher temporal resolution, existing SNN models do not attach importance to that the serial frames have different signal-to-noise ratios since event streams are sparse and non-uniform.
Biological spiking neurons with intrinsic dynamics underlie the powerful representation and learning capabilities of the brain for processing multimodal information in complex environments.
In summary, the EOQ framework is specially designed for reducing the high cost of convolution and BN in network training, demonstrating a broad application prospect of online training in resource-limited devices.
Graph Convolutional Networks (GCNs) have received significant attention from various research fields due to the excellent performance in learning graph representations.
Moreover, analysis on the activation's mean in the forward pass reveals that the self-normalization property gets weaker with larger fan-in of each layer, which explains the performance degradation on large benchmarks like ImageNet.
However, neural network quantization can be used to reduce computation load while maintaining comparable accuracy and original network structure.
To address this issue, in this work, we propose a Leaky Integrate and Analog Fire (LIAF) neuron model, so that analog values can be transmitted among neurons, and a deep network termed as LIAF-Net is built on it for efficient spatiotemporal processing.
To this end, we propose a threshold-dependent batch normalization (tdBN) method based on the emerging spatio-temporal backpropagation, termed "STBP-tdBN", enabling direct training of a very deep SNN and the efficient implementation of its inference on neuromorphic hardware.
In this paper, we restore the negative information in few-shot object detection by introducing a new negative- and positive-representative based metric learning framework and a new inference scheme with negative and positive representatives.
Recurrent neural networks (RNNs) are powerful in the tasks oriented to sequential data, such as natural language processing and video recognition.
We further theoretically and experimentally discover that the HT format has better performance on compressing weight matrices, while the TT format is more suited for compressing convolutional kernels.
We demonstrate the advantages of this model in multiple different tasks, including few-shot learning, continual learning, and fault-tolerance learning in neuromorphic vision sensors.
Neuromorphic data, recording frameless spike events, have attracted considerable attention for the spatiotemporal information components and the event-driven processing fashion.
Recently, backpropagation through time inspired learning algorithms are widely introduced into SNNs to improve the performance, which brings the possibility to attack the models accurately given Spatio-temporal gradient maps.
Powered by our metric and framework, we analyze extensive initialization, normalization, and network structures.
In summary, this work provides a new solution for lensless imaging through scattering media using transfer learning in DNNs.
Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability.
However, due to the higher dimension of convolutional kernels, the space complexity of 3DCNNs is generally larger than that of traditional two dimensional convolutional neural networks (2DCNNs).
As well known, the huge memory and compute costs of both artificial neural networks (ANNs) and spiking neural networks (SNNs) greatly hinder their deployment on edge devices with high efficiency.
To the best of our knowledge, DashNet is the first framework that can integrate and process ANNs and SNNs in a hybrid paradigm, which provides a novel solution to achieve both effectiveness and efficiency for high-speed object tracking.
In this way, all the operations in the training and inference can be bit-wise operations, pushing towards faster processing speed, decreased memory cost, and higher energy efficiency.
Spiking neural networks (SNNs) represent the most prominent biologically inspired computing model for neuromorphic computing (NC) architectures.
We identify that the effectiveness expects less data correlation while the efficiency expects regular execution pattern.
Deep spiking neural networks (SNNs) support asynchronous event-driven computation, massive parallelism and demonstrate great potential to improve the energy efficiency of its synchronous analog counterpart.
For example, we improve the perplexity per word (PPW) of a ternary LSTM on Penn Tree Bank (PTB) corpus from 126 (the state-of-the-art result to the best of our knowledge) to 110. 3 with a full precision model in 97. 2, and a ternary GRU from 142 to 113. 5 with a full precision model in 102. 7.
We propose to execute deep neural networks (DNNs) with dynamic and sparse graph (DSG) structure for compressive memory and accelerative execution during both training and inference.
Spiking neural networks (SNNs) that enables energy efficient implementation on emerging neuromorphic hardware are gaining more attention.
Crossbar architecture based devices have been widely adopted in neural network accelerators by taking advantage of the high efficiency on vector-matrix multiplication (VMM) operations.
Batch Normalization (BN) has been proven to be quite effective at accelerating and improving the training of deep neural networks (DNNs).
Researches on deep neural networks with discrete parameters and their deployment in embedded systems have been active and promising topics.
Firstly, the event number of each pixel of the HR DVS image is determined with a sparse signal representation based method to obtain the HR event-count map from that of the LR DVS recording.
By simultaneously considering the layer-by-layer spatial domain (SD) and the timing-dependent temporal domain (TD) in the training phase, as well as an approximated derivative for the spike activity, we propose a spatio-temporal backpropagation (STBP) training framework without using any complicated technology.
Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github. com/AcrossV/Gated-XNOR.