This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper introduces a framework to quantify information processing capacity in reservoir computing based on eigen-spectral decomposition, revealing vulnerabilities of low-energy modes.

The paper introduces an adaptive reservoir computing framework that tailors Echo State Networks (ESNs) to specific evaluation scenarios, achieving a high score on the CTF-4-Science Lorenz benchmark fo…

The paper proposes CYKNN, a novel recurrent neural network architecture that directly encodes the CYK parsing algorithm, demonstrating superior performance over large language models on syntactic pars…

This paper introduces a mechanistic neuronal network model for multilayer learning, offering biological insights and an alternative to backpropagation.

Echo is a joint-embedding predictive architecture that uses a single, pretrained ViT encoder to simultaneously perform speaker diarization, speech recognition, and dynamic source separation in a share…

A new error backpropagation method called supervised counterstream learning is proposed for deep associative networks, which only requires recognition of errors during training and backpropagates corr…

This paper compares the cost-performance trade-off of Hebbian learning, Dense Difference Target Propagation (DDTP), and backpropagation (BP) using mutual-information-based measures.

The paper proposes a unified framework for designing efficient and expressive token mixing layers by separating the direct and recurrent influences of inputs, allowing for a principled trade-off betwe…

The paper provides a unified algebraic framework to determine the formal language expressivity of recurrent neural language models, resolving conflicts in existing literature by linking expressivity t…

This paper identifies and quantifies two structural bottlenecks in certain state-of-the-art neural audio models that limit access to frequency-localized primitives, and proposes a lightweight interven…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

This paper proposes a sparse cache with a novel allocation rule based on DP-means clustering for deep recurrent models, achieving full associative recall with only distinct items, outperforming other…

Clark Hash is a stateless, deterministic quantization method that significantly reduces the storage size of neural embeddings while maintaining high accuracy for cosine similarity search.

The paper introduces partial multi-neuron relaxation, a novel verification technique that selectively computes tight linear bounds for a small subset of neurons to improve the efficiency and tightness…

This paper proposes RPPNet, a two-stage deep learning architecture for music generation with variable structural boundaries, which automatically derives grouping of Rhythm-Pitch Primitive sequences fr…

This paper proposes cumsum-composable phase transport, a streaming-native temporal layer for keyword spotting using unitary transport, prefix differences, and gated residual updates.

This paper proposes a new definition of source in source tracing as a compositional tuple of Architecture, Training Data, and other training factors, and introduces a framework using Structured Orthon…

CARE-DPP is a batch active-learning method for eco-acoustic monitoring that combines predictive uncertainty and embedding-space novelty with a determinantal point process objective.