Spikify is a Python library designed to transform raw data into spike-based signals for use in neuromorphic computing and spiking neural network (SNN) applications. The tool provides a suite of encoding algorithms that convert continuous signals into spike representations, supporting efficient and biologically inspired computation. Spikify is intended for users working with either real-time or offline data who require flexible and customizable spike encoding tailored to specific data characteristics and application needs.
The platform offers a variety of encoding schemes, including rate coding, Poisson encoding, temporal coding, contrast-based methods, moving window encoding, step forward encoding, threshold-based representation, zero-crossing step-forward encoding, latency-based approaches, burst coding, global reference methods, phase encoding, time-to-first-spike encoding, and several deconvolution-based techniques such as Ben’s Spiker Algorithm, Hough Spiker, and Modified Hough Spiker. These options allow users to select and apply the most appropriate algorithm for their particular use case, providing full control over the encoding process. Spikify also includes optional filtering capabilities inspired by the human cochlea, which can be used to preprocess signals and enhance the quality and relevance of the generated spikes.
Integration with spiking neural network models is a key feature, enabling generated spike trains to be directly fed into SNN workflows for both research and practical applications. The library supports end-to-end design processes, and can be paired with deployment and benchmarking tools such as NIR and NeuroBench for comprehensive evaluation. Spikify is inspired by published research on spike encoding techniques for IoT time-varying signals, highlighting its grounding in current neuromorphic computing methodologies.
Spikify is delivered as a Python library and is documented online.
In the Frameworks & SDKs space, spikify documentation takes a focused approach. It focuses on enabling researchers to encode and decode neural signals using spike-based methods in Python. spikify documentation is an open-source project aimed at neuroscience researchers and Python developers. The project is open source (Apache-2.0). spikify documentation is available on the web and the command line, and it can be self-hosted.
spikify documentation first shipped in 2024. The project is developed in the open on GitHub with 36 commits in the last 90 days. Among its 5 catalogued features are spike encoding, spike decoding, and Python API.
Latest indexed changes and source events
Other apps tracked under the same category.
