Researchers introduced the input-skip LBBNN (ISLaB) technique, which reduces neural network complexity by over 99% while maintaining accuracy, achieving 97% accuracy on MNIST with only 935 weights. Th…
Researchers have developed quantum Wasserstein generative adversarial networks (GANs) that generate full-resolution MNIST images without dimensionality reduction or patchwork models, achieving state-o…
Researchers introduced Meta Neural Cellular Automata (MetaNCA), a framework that learns local rules to self-organize the weights of artificial neural networks without backpropagation. The method gener…
Researchers proposed a controllability-observability framework for compressing deep neural networks by viewing them as nonlinear dynamical systems. The method achieved up to 83% parameter compression …
Researchers introduced Sheaf-ADMM, a framework for multi-agent coordination that divides complex tasks into overlapping pieces assigned to individual agents. In tests, it achieved a 93% solve rate on …
Researchers propose S-GAI, a spectral geometry-aware initialization framework for sigmoidal MLPs that encodes dataset geometry into network weights. Using SVD to extract class-wise spectral features, …
Researchers introduced Pre-Warm, a zero-training-cost method for data-conditioned initialization of the first convolutional layer in CNNs. The technique clusters patches from a single training batch t…
Researchers introduced the apothem measure for computing robustness certifications in neural networks, achieving optimal certifications with linear oracle calls. They proved volume-optimal oracle-base…
Neural Cellular Automata (NCA) extend Conway's Game of Life by learning neural network weights to solve problems like MNIST digit classification, maze solving, and playing Pong. NCA use local receptiv…
Researchers introduced SupraSNN, a hardware-software co-design that treats synaptic events as parallelizable micro-operations and physically decouples synaptic and neuronal computation, achieving syna…
A developer has demonstrated that the 1982 Hopfield associative memory update rule and the 2017 Transformer scaled dot-product attention mechanism are mathematically identical operations, with one equ…
A systematic study of query, key, and value (QKV) projection variants in Transformers found that sharing the key and value projections (Q-K=V) performs on par with or better than the standard three-pr…
Researchers have developed a tensor similarity method that can detect changes in neural network behavior, such as backdoor attacks, by comparing the weight-space structure of models rather than just t…
Researchers developed Riemannian Archetypal Analysis, a method that combines the interpretability of classical archetypal analysis with the flexibility of non-linear models by using data-driven pullba…
The author successfully ran MNIST digit recognition on an ESP32-C3 microcontroller by compiling a neural network directly into a C header file and executing it as firmware, without using TensorFlow, T…
Deep neural networks can be understood as pipelines of simple functions, and that the intermediate values (or "activations") within these networks can be viewed as high-dimensional vectors. To analyze…