Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks [PDF]
International Conference on Learning Representations, 2023 Spiking Neural Networks (SNNs) have gained great attraction due to their distinctive properties of low power consumption and fast inference on neuromorphic hardware.
Tong Bu +5 more
semanticscholar +1 more source
Fast-SNN: Fast Spiking Neural Network by Converting Quantized ANN [PDF]
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023 Spiking neural networks (SNNs) have shown advantages in computation and energy efficiency over traditional artificial neural networks (ANNs) thanks to their event-driven representations.
Yang‐Zhi Hu +3 more
semanticscholar +1 more source
Reducing ANN-SNN Conversion Error through Residual Membrane Potential [PDF]
AAAI Conference on Artificial Intelligence, 2023 Spiking Neural Networks (SNNs) have received extensive academic attention due to the unique properties of low power consumption and high-speed computing on neuromorphic chips.
Zecheng Hao +4 more
semanticscholar +1 more source
Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks [PDF]
International Joint Conference on Artificial Intelligence, 2021 Spiking Neural Networks (SNNs), as bio-inspired energy-efficient neural networks, have attracted great attentions from researchers and industry. The most efficient way to train deep SNNs is through ANN-SNN conversion.
Jianhao Ding +3 more
semanticscholar +1 more source
FE $${}^\textrm{ANN}$$ ANN : an efficient data-driven multiscale approach based on physics-constrained neural networks and automated data mining [PDF]
Computational Mechanics, 2022 Herein, we present a new data-driven multiscale framework called FE $${}^\textrm{ANN}$$ ANN which is based on two main keystones: the usage of physics-constrained artificial neural networks (ANNs) as macroscopic surrogate models and an autonomous data ...
K. Kalina +3 more
semanticscholar +1 more source
International Journal of Production Research, 2022 This study posits that the use of artificial intelligence (AI) enables supply chains (SCs) to dynamically react to volatile environments, and alleviate potentially costly decision-makings for small-medium enterprises (SMEs).
Lai-Wan Wong +4 more
semanticscholar +1 more source
Use of ANFIS/Genetic Algorithm and Neural Network to Predict Inorganic Indicators of Water Quality [PDF]
Journal of Chemical and Petroleum Engineering, 2020 The present research used novel hybrid computational intelligence (CI) models to predict inorganic indicators of water quality. Two CI models i.e. artificial neural network (ANN) and a hybrid adaptive neuro-fuzzy inference system (ANFIS) trained by ...
Majid Mohadesi, Babak Aghel
doaj +1 more source
ANN-Benchmarks: A Benchmarking Tool for Approximate Nearest Neighbor Algorithms [PDF]
Similarity Search and Applications, 2018 This paper describes ANN-Benchmarks, a tool for evaluating the performance of in-memory approximate nearest neighbor algorithms. It provides a standard interface for measuring the performance and quality achieved by nearest neighbor algorithms on ...
Martin Aumüller +2 more
semanticscholar +1 more source
Experimental investigation on utilization of substitute building materials in concrete using neural networks [PDF]
E3S Web of ConferencesThe replacement of cement with sugarcane bagasse ash in concrete is considered due to its rich properties of projecting pozzolanic activity. The availability of aggregates is becoming scarce as a result of the non-renewable characteristic of fine and ...
Kumar V Prem +6 more
doaj +1 more source
Inform: Jurnal Ilmiah Bidang Teknologi Informasi dan Komunikasi, 2020 Folding machine is a tool that is needed in the small and medium scale laundry industry that has a goal for the efficiency of production time. The flip folder is the main component of this tool, which functions to fold the clothes by moving to form a ...
Yuliyanto Agung Prabowo +2 more
doaj +1 more source