Gabriel Béna 🌻

@solarpunkgabs.bsky.social

390 Followers 401 Following

PhD Student at Imperial College with Dan Goodman. Pretending to be a neuro guy. Modularity, structure-function, resource-constrained ANNs/SNNs, neuromorphic + fun stuff like Neural Cellular Automatas 😎 Also working w/ SpiNNCloud on SpiNNaker2.

BUT CAN IT RUN DOOOOOOM ??

Graph-based task representations and GNN-based hypernetwork for hardware generation

Examples of an Out of Distribution Task: the NCA needs to distribute a matrix in all corners in a larger grid than the one seen during training.

NCAs as a neural network emulator. Inputs show a batch of flattened MNIST images, alongside the weight matrix of a pre-trained single-layer linear classifier. We decompose this matrix multiplication into sub-blocks, that can be directly emulated in parallel by the NCA. Results are fetched from NCA states and aggregated back into logits, of size batch x 10 (figure shows the first 32 outputs only for readability). We compute accuracy by taking the logits argmax per batch and comparing with labels.

Neural Cellular Automata performing matrix rotation. The NCA learns to rotate the input matrix by 90 degrees.

Our framework performs matrix operations (translation, multiplication, rotation) through continuous cellular interactions evolving over time (from t=0 to t=60). Core mechanism: cells communicating only with neighbors, and interacting with a local fixed (but learned) heterogeneous substrate, are able to collectively solve mathematical tasks without explicit algorithms.

Accuracy comparison between the on and off chip implementations, for both the full dataset or the reduced dataset. Both show minimal differences and good accuracy.

Software and Hardware stack of the implementation.