Category: machine learning

BitNetMCU with CNN: >99.5% MNIST accuracy on a low-end Microcontroller

Combining a deep-depthwise CNN architecture with variable quantization in BitNetMCU achieves state-of-the-art MNIST accuracy on a low-end 32-bit microcontroller with 4 kB RAM and 16 kB flash.

Read the article at my new blog location.

Neural Network Visualization

Going along with implementing a very size optimized neural network on a 3 cent microcontroller I created an interactive simulation of a similar network.

You can draw figures on a 8×8 pixel grid and view how the activations propagate through the multi-layer perception network to classify the image into 4 or 10 different numbers. You can find the visualizer online here.

Continue reading “Neural Network Visualization”