https://blog.ast.moe/en/tags/analog-circuits/Recent posts: GorimuchuHugohttps://blog.ast.moe/en/blog/2026-08-13/Thu, 13 Aug 2026 20:59:43 +0900https://blog.ast.moe/en/blog/2026-08-13/<p>Last time we discussed how combining multiplication based on Ohm’s law with addition based on Kirchhoff’s current law could enable us to represent the neural network’s multiply‑accumulate operation in a physical circuit.</p> <p>This time, assuming we will eventually build an actual hardware circuit, we first consider the minimal circuit configuration.</p> <p>In this simulator we will keep the resistor values fixed and dynamically vary the voltage output from the microcontroller.</p> <p>With this setup, the weight updates and multiplications are performed on the microcontroller side, while the analog circuit handles voltage summation and inversion. We’re not trying to implement all of machine learning with an analog circuit, but this level of setup should be sufficient for first confirming the correspondence between the equations and the circuit.</p>https://blog.ast.moe/en/blog/2026-08-12-2/Wed, 12 Aug 2026 21:01:23 +0900https://blog.ast.moe/en/blog/2026-08-12-2/<h2 id="wouldnt-it-be-interesting-to-do-machine-learning-with-analog-circuits">Wouldn&rsquo;t it be interesting to do machine learning with analog circuits?</h2> <p>Lately, large language models have become popular, but they require a lot of GPUs, money, and electricity. I thought it would be fascinating to try doing this with analog circuits.</p> <p>The calculations performed by neural networks are essentially multiplication and addition.</p> <p>So, this time I’ll give a rough overview starting from the basic theory.</p> <h2 id="what-is-analog-computation">What is analog computation?</h2> <p>In digital computers, numbers are represented as combinations of 0s and 1s. Even if the voltage changes slightly during a calculation, the original information can be recovered as long as the change stays within the range where 0 and 1 can still be distinguished.</p>