Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial · HackerPapers discussions

Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial — mentioned by rsfern

Sun, 30 Jun 2024 12:22:25 GMT

This is really cool, but I was confused by the framing as a resistor network since I think that should be linear (to first order? I’m not an EE) What they have is a transistor network, and they constrain all the transistors to the ohmic regime, so now the resistivity of an individual transistor can be some nonlinear function of its inputs, which is really cool, like detuning transistors to do analog computation instead of digital. Here’s the preprint: https://arxiv.org/abs/2311.00537

Paper and discussion history. A mention is not an endorsement.

Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial — HN submission

Sun, 09 Jun 2024 14:56:43 GMT

Machine Learning Without Processor: Emergent Learning in Electronic Metamaterial

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

Machine Learning Without a Processor: Emergent Learning in a Nonlinear Electronic Metamaterial — mentioned by av3csr

Thu, 06 Jun 2024 08:07:23 GMT

https://arxiv.org/pdf/2311.00537

Paper and discussion history. A mention is not an endorsement.