|
|
|
|
|
Gulsum Alicioglu and Bo Sun
Deep learning (DL) models have achieved state-of-the-art performance in many domains. The interpretation of their working mechanisms and decision-making process is essential because of their complex structure and black-box nature, especially for sensitiv...
ver más
|
|
|
|
|
|
|
|
|
|
|
Tushar Ganguli and Edwin K. P. Chong
We present a novel technique for pruning called activation-based pruning to effectively prune fully connected feedforward neural networks for multi-object classification. Our technique is based on the number of times each neuron is activated during model...
ver más
|
|
|
|
|
|
|
|
|
|
|
Angeliki Bicaku, Maria Sapounaki, Athanasios Kakarountas and Sotiris K. Tasoulis
Throughout the last decades, neuromorphic circuits have incited the interest of scientists, as they are potentially a powerful tool for the treatment of neurological diseases. To this end, it is essential to consider the biological principles of the CNS ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Jörg P. Kotthaus
An acoustoelectric approach to neuron function is proposed that combines aspects of the widely accepted electrical-circuit-based Hodgkin?Huxley model for the generation and propagation of action potentials via electric polarization with mechanical models...
ver más
|
|
|
|
|
|
|
|
|
|
|
Jean Flores-Gómez, Mario Villegas-Ruvalcaba, José Blancas-Flores and Juan Morales-Rivera
In this study, a novel chitosan?resole?pectin aerogel (CS?R?P) was created from a sol?gel reaction with a solution of Cs and P with resole by a freeze-drying technique, and this adsorbent was proposed for the removal of methylene blue (MB). In addition, ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Wieslaw L. Nowinski
Although no dataset at the nanoscale for the entire human brain has yet been acquired and neither a nanoscale human whole brain atlas has been constructed, tremendous progress in neuroimaging and high-performance computing makes them feasible in the non-...
ver más
|
|
|
|
|
|
|
|
|
|
|
Xiaochuan Sun, Jiahui Gao and Yu Wang
During the deployment of practical applications, reservoir computing (RC) is highly susceptible to radiation effects, temperature changes, and other factors. Normal reservoirs are difficult to vouch for. To solve this problem, this paper proposed a rando...
ver más
|
|
|
|
|
|
|
|
|
|
|
Arash Khajooei, Mohammad (Behdad) Jamshidi and Shahriar B. Shokouhi
Although the Metaverse is becoming a popular technology in many aspects of our lives, there are some drawbacks to its implementation on clouds, including long latency, security concerns, and centralized infrastructures. Therefore, designing scalable Meta...
ver más
|
|
|
|
|
|
|
|
|
|
|
John S. Venker, Luke Vincent and Jeff Dix
A Spiking Neural Network (SNN) is realized within a 65 nm CMOS process to demonstrate the feasibility of its constituent cells. Analog hardware neural networks have shown improved energy efficiency in edge computing for real-time-inference applications, ...
ver más
|
|
|
|
|
|
|
|
|
|
|
Arash Khajooei Nejad, Mohammad (Behdad) Jamshidi and Shahriar B. Shokouhi
This paper introduces Tensor-Organized Memory (TOM), a novel neuromorphic architecture inspired by the human brain?s structural and functional principles. Utilizing spike-timing-dependent plasticity (STDP) and Hebbian rules, TOM exhibits cognitive behavi...
ver más
|
|
|
|
|
|