A re-implementation of Karpathy's micrograd in C
Micrograd ported to C with manual memory management via reference counting.
C programmers learning backpropagation internals
micrograd
Takes micrograd's toy autodiff idea and scales it to real tensor operations with NumPy and optional CuPy GPU support. The repo exposes an nn-like module, common activations (ReLU/Softmax), self-attention and an MNIST MLP example, so it's excellent as a learning resource. It's explicitly flagged as WIP — expect performance and OOM rough edges, so treat it as a study tool rather than a training backbone.
Educational Mars sim, but page content doesn't match the project title.
Research-as-loss-function lets stale-knowledge agents guide health optimization via gradients.
Rust SIMD intrinsics can compile without warnings but produce zero vectorized instructions.
WebGL 2 instanced rendering optimization of a known tool, not a novel approach.
MAP-Elites database beats TSV logging for evolutionary search tracking.
