Related papers: Temporal-Rate Encoding to Realize Unary Positional…

Current state-of-the-art methods of image classification using convolutional neural networks are often constrained by both latency and power consumption. This places a limit on the devices, particularly low-power edge devices, that can…

In this paper, we propose a new hybrid temporal computing (HTC) framework that leverages both pulse rate and temporal data encoding to design ultra-low energy hardware accelerators. Our approach is inspired by the recently proposed temporal…

This paper proposes a definition of what it means for one system description language to encode another one, thereby enabling an ordering of system description languages with respect to expressive power. I compare the proposed definition…

In the context of lossy compression, Blau & Michaeli (2019) adopt a mathematical notion of perceptual quality and define the information rate-distortion-perception function, generalizing the classical rate-distortion tradeoff. We consider…

In recent years, Spiking Neural Networks (SNNs) have gathered significant interest due to their temporal understanding capabilities. This work introduces, to the best of our knowledge, the first Cortical Column like hybrid architecture for…

We propose a novel backpropagation algorithm for training spiking neural networks (SNNs) that encodes information in the relative multiple spike timing of individual neurons without single-spike restrictions. The proposed algorithm inherits…

Spiking neural networks (SNNs) exhibit temporal, sparse, and event-driven dynamics that make them appealing for efficient inference. However, extending these models to self-supervised regimes remains challenging because the discontinuities…

Spiking Neural P systems, SNP systems for short, are biologically inspired computing devices based on how neurons perform computations. SNP systems use only one type of symbol, the spike, in the computations. Information is encoded in the…

To understand possible strategies of temporal spike coding in the central nervous system, we study functional neuromimetic models of visual processing for static images. We will first present the retinal model which was introduced by Van…

Embedding methods such as word embedding have become pillars for many applications containing discrete structures. Conventional embedding methods directly associate each symbol with a continuous embedding vector, which is equivalent to…

This paper describes a new method of data encoding which may be used in various modern digital, computer and telecommunication systems and devices. The method permits the compression of data for storage or transmission, allowing the exact…

Transformers achieve remarkable performance in various domains, including NLP, CV, audio processing, and graph analysis. However, they do not scale well on long sequence tasks due to their quadratic complexity w.r.t. the inputs length.…

Unified multimodal models (UMMs) aim to jointly perform multimodal understanding and generation within a single framework. We present TUNA, a native UMM that builds a unified continuous visual representation by cascading a VAE encoder with…

This invention addresses fixed-point representations of convolutional neural networks (CNN) in integrated circuits. When quantizing a CNN for a practical implementation there is a trade-off between the precision used for operations between…

Due to its conceptual simplicity and generality, compressive neural representation has emerged as a promising alternative to traditional compression methods for managing massive volumetric datasets. The current practice of neural…

The efficiency of modern machine intelligence depends on high accuracy with minimal computational cost. In spiking neural networks (SNNs), synaptic delays are crucial for encoding temporal structure, yet existing models treat them as fully…

Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to…

In coding theory, an error-correcting code can be encoded either systematically or non-systematically. In a systematic encode, the input data is embedded in the encoded output. Conversely, in a non-systematic code, the output does not…

Recently, many neural network-based image compression methods have shown promising results superior to the existing tool-based conventional codecs. However, most of them are often trained as separate models for different target bit rates,…

Inductive representation learning on temporal heterogeneous graphs is crucial for scalable deep learning on heterogeneous information networks (HINs) which are time-varying, such as citation networks. However, most existing approaches are…