Zobrazeno 1 - 10
of 229
pro vyhledávání: '"Rajendran, Bipin"'
This paper introduces Xpikeformer, a hybrid analog-digital hardware architecture designed to accelerate spiking neural network (SNN)-based transformer models. By combining the energy efficiency and temporal dynamics of SNNs with the powerful sequence
Externí odkaz:
http://arxiv.org/abs/2408.08794
Common artefacts such as baseline drift, rescaling, and noise critically limit the performance of machine learningbased automated ECG analysis and interpretation. This study proposes Derived Peak (DP) encoding, a non-parametric method that generates
Externí odkaz:
http://arxiv.org/abs/2405.00724
In-context learning (ICL), a property demonstrated by transformer-based sequence models, refers to the automatic inference of an input-output mapping based on examples of the mapping provided as context. ICL requires no explicit learning, i.e., no ex
Externí odkaz:
http://arxiv.org/abs/2404.06469
Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using spiking signa
Externí odkaz:
http://arxiv.org/abs/2402.09109
Autor:
Katti, Prabodh, Nimbekar, Anagha, Li, Chen, Acharyya, Amit, Al-Hashimi, Bashir M., Rajendran, Bipin
Bayesian neural networks offer better estimates of model uncertainty compared to frequentist networks. However, inference involving Bayesian models requires multiple instantiations or sampling of the network parameters, requiring significant computat
Externí odkaz:
http://arxiv.org/abs/2401.15453
Autor:
Li, Chen, Rajendran, Bipin
Recent strides in low-latency spiking neural network (SNN) algorithms have drawn significant interest, particularly due to their event-driven computing nature and fast inference capability. One of the most efficient ways to construct a low-latency SN
Externí odkaz:
http://arxiv.org/abs/2312.05290
Artificial intelligence (AI) algorithms based on neural networks have been designed for decades with the goal of maximising some measure of accuracy. This has led to two undesired effects. First, model complexity has risen exponentially when measured
Externí odkaz:
http://arxiv.org/abs/2309.15942
Autor:
Ortiz, Flor, Skatchkovsky, Nicolas, Lagunas, Eva, Martins, Wallace A., Eappen, Geoffrey, Daoud, Saed, Simeone, Osvaldo, Rajendran, Bipin, Chatzinotas, Symeon
The latest satellite communication (SatCom) missions are characterized by a fully reconfigurable on-board software-defined payload, capable of adapting radio resources to the temporal and spatial variations of the system traffic. As pure optimization
Externí odkaz:
http://arxiv.org/abs/2308.11152
Autor:
Ai, Yiming, Rajendran, Bipin
Brain-computer interfaces are being explored for a wide variety of therapeutic applications. Typically, this involves measuring and analyzing continuous-time electrical brain activity via techniques such as electrocorticogram (ECoG) or electroencepha
Externí odkaz:
http://arxiv.org/abs/2304.11106
Publikováno v:
Thakar et al., npj 2D Mater Appl 7, 68 (2023)
Accurate, timely and selective detection of moving obstacles is crucial for reliable collision avoidance in autonomous robots. The area- and energy-inefficiency of CMOS-based spiking neurons for obstacle detection can be addressed through the reconfi
Externí odkaz:
http://arxiv.org/abs/2302.02095