{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/bindsnet-a-machine-learning-oriented-spiking","title":"BindsNET: A machine learning-oriented spiking neural networks library in Python","arxiv_id":"1806.01423","date":"2018-06-04","proceeding":null,"authors":["Hananel Hazan","Daniel J. Saunders","Hassaan Khan","Darpan T. Sanghavi","Hava T. Siegelmann","Robert Kozma"],"abstract":"The development of spiking neural network simulation software is a critical\ncomponent enabling the modeling of neural systems and the development of\nbiologically inspired algorithms. Existing software frameworks support a wide\nrange of neural functionality, software abstraction levels, and hardware\ndevices, yet are typically not suitable for rapid prototyping or application to\nproblems in the domain of machine learning. In this paper, we describe a new\nPython package for the simulation of spiking neural networks, specifically\ngeared towards machine learning and reinforcement learning. Our software,\ncalled BindsNET, enables rapid building and simulation of spiking networks and\nfeatures user-friendly, concise syntax. BindsNET is built on top of the PyTorch\ndeep neural networks library, enabling fast CPU and GPU computation for large\nspiking networks. The BindsNET framework can be adjusted to meet the needs of\nother existing computing and hardware environments, e.g., TensorFlow. We also\nprovide an interface into the OpenAI gym library, allowing for training and\nevaluation of spiking networks on reinforcement learning problems. We argue\nthat this package facilitates the use of spiking networks for large-scale\nmachine learning experimentation, and show some simple examples of how we\nenvision BindsNET can be used in practice. BindsNET code is available at\nhttps://github.com/Hananel-Hazan/bindsnet","url_abs":"http://arxiv.org/abs/1806.01423v2","url_pdf":"http://arxiv.org/pdf/1806.01423v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"bindsnet-a-machine-learning-oriented-spiking","repo_url":"https://github.com/Hananel-Hazan/bindsnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"AGPL-3.0"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":null,"task_name":"CPU"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"neural-network-simulation","task_name":"Neural Network simulation"},{"task_slug":"openai-gym","task_name":"OpenAI Gym"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.01423","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}