Introduction¶
Transforming Raw Data into Spiking Signals
Get ready for neuromorphic computing: convert your data into spike-based signals for efficient and biologically-inspired spiking neural network applications, enabling faster and more energy-efficient computations.
Transform raw signals into spikes with encoding algorithms tailored to different data characteristics and application needs.
Select the encoding algorithm that best suits your needs and apply it with ease and full control.
Leverage optional filtering inspired by the human cochlea to preprocess your signals, enhancing the quality and relevance of the generated spikes.
Directly feed the generated spikes into spiking neural network models, ensuring a smooth and efficient workflow from signal to network.
Whether you’re working with real-time or offline data, spikify offers the flexibility you need for your SNN application.
Empower your end-to-end design with deployment and benchmarking tools: couple spikify with NIR and NeuroBench.
Inspiration¶
The spikify library is inspired by the paper “Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task”, which explores various methods for converting continuous signals into spike-based representations for neuromorphic computing.
Citation¶
If you use the spikify library in your research or applications, please cite the following paper:
@ARTICLE{
10.3389/fnins.2022.999029,
AUTHOR={Forno, Evelina and Fra, Vittorio and Pignari, Riccardo and Macii, Enrico and Urgese, Gianvito },
TITLE={Spike encoding techniques for IoT time-varying signals benchmarked on a neuromorphic classification task},
JOURNAL={Frontiers in Neuroscience},
VOLUME={16},
YEAR={2022},
URL={https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2022.999029},
DOI={10.3389/fnins.2022.999029},
ISSN={1662-453X},
}
Referenced By:¶
The following research has cited this work and contributed to the field of neuromorphic computing and spiking neural networks. This growing body of literature continues to expand on the concepts and methodologies introduced in the referenced paper, driving further advancements in the area.
On the Sampling Sparsity of Neuromorphic Analog-to-Spike Conversion based on Leaky Integrate-and-Fire by B. A. Moser, M. Lunglmayr (2024)
Situational Awareness Classification Based on EEG Signals and Spiking Neural Network by Yakir Hadad, Moshe Bensimon, Y. Ben-Shimol, S. Greenberg (2024)
Adaptive Synaptic Adjustment Mechanism to Improve Learning Performances of Spiking Neural Networks by Hyun-Jong Lee, Jae-Han Lim (2024)
WiN-GUI: A graphical tool for neuron-based encoding by Simon F. Müller-Cleve, Fernando M. Quintana, Vittorio Fra, Pedro L. Galindo, Fernando Perez-Peña, Gianvito Urgese, Chiara Bartolozzi (2024)
Rapid Distance Estimation of Odor Sources by Electronic Nose with Multi-Sensor Fusion based on Spiking Neural Network by Yingying Xue, Shimeng Mou, Changming Chen, Weijie Yu, Hao Wan, L. Zhuang, Ping Wang (2024)
Evaluation of Encoding Schemes on Ubiquitous Sensor Signal for Spiking Neural Network by Sizhen Bian, Elisa Donati, Michele Magno (2024)
Spiking neural networks for physiological and speech signals: a review by Sung Soo Park, Young-Seok Choi (2024)
Quantization-Aware Training of Spiking Neural Networks for Energy-Efficient Spectrum Sensing on Loihi Chip by Shiya Liu, N. Mohammadi, Yang Yi (2024)
Unleashing the potential of spiking neural networks for epileptic seizure detection: A comprehensive review by Resmi Cherian, G. Kanaga E (2024)
Effects of RF Signal Eventization Encoding on Device Classification Performance by Michael J. Smith, Michael A. Temple, James W. Dean (2024)
Integrating a hippocampus memory model into a neuromorphic robotic-arm for trajectory navigation by D. Casanueva‐Morato, Pablo Lopez-Osorio, E. Piñero-Fuentes, J. P. Dominguez-Morales, Fernando Perez-Peña, Alejandro Linares-Barranco (2024)
Investigating the Use of Low-Cost Tactile Sensor in Emulating Mechanoreceptor Patterns and in Hardness-Based Classification by Yash Sharma, Pedro Ferreira, Laura Justham, Matthew Beatty (2024)
An ultra low power spiking neural encoder of microwave signals by Christophe Loyez, François Danneville (2024)
DNN-SNN Co-Learning for Sustainable Symbol Detection in 5G Systems on Loihi Chip by Shiya Liu, Yibin Liang, Yang Yi (2024)
Review of open neuromorphic architectures and a first integration in the RISC-V PULP platform by Michelangelo Barocci, Vittorio Fra, Enrico Macii, Gianvito Urgese (2023)
Neuromorphic intermediate representation: A unified instruction set for interoperable brain-inspired computing by Jens Egholm Pedersen, Steven Abreu, Matthias Jobst, Gregor Lenz, Vittorio Fra, F. Bauer, Dylan R. Muir, Peng Zhou, B. Vogginger, Kade Heckel, Gianvito Urgese, Sadasivan Shankar, Terrence C. Stewart, J. Eshraghian, Sadique Sheik (2023)
Integrate-and-fire circuit for converting analog signals to spikes using phase encoding by Javier Lopez-Randulfe, Nico Reeb, Alois Knoll (2023)
SPAIC: A sub-μW/Channel, 16-Channel General-Purpose Event-Based Analog Front-End with Dual-Mode Encoders by Shyam Narayanan, M. Cartiglia, Arianna Rubino, Charles Lego, Charlotte Frenkel, G. Indiveri (2023)
Efficiency metrics for auditory neuromorphic spike encoding techniques using information theory by Ahmad El Ferdaoussi, J. Rouat, É. Plourde (2023)
Integration of neuromorphic AI in event-driven distributed digitized systems: Concepts and research directions by Mattias Nilsson, Olov Schel’en, Anders Lindgren, Ulf Bodin, Cristina Paniagua, J. Delsing, Fredrik Sandin (2022)
Contents¶
Overview
API
Development