2 citations · 2 across the 32 of their papers we have counts for
14 papers · 1 filter
Data-Driven Variational Basis Learning Beyond Neural Networks: A Non-Neural Framework for Adaptive Basis Discovery
Andrew Kiruluta
Classical representation systems such as Fourier series, wavelets, and fixed dictionaries provide analytically tractable basis expansions, but they are not intrinsically adapted to…
From Gradients to Riccati Geometry: Kalman World Models for Single-Pass Learning
Andrew Kiruluta
Backpropagation dominates modern machine learning, yet it is not the only principled method for optimizing dynamical systems. We propose Kalman World Models (KWM), a class of learn…
Spectral Generative Flow Models: A Physics-Inspired Replacement for Vectorized Large Language Models
Andrew Kiruluta
We introduce Spectral Generative Flow Models (SGFMs), a physics-inspired alternative to transformer-based large language models. Instead of representing text or video as sequences…
Filtering Beats Fine Tuning: A Bayesian Kalman View of In Context Learning in LLMs
Andrew Kiruluta
We present a theory-first framework that interprets inference-time adaptation in large language models (LLMs) as online Bayesian state estimation. Rather than modeling rapid adapta…
Quantum Spectral Reasoning: A Non-Neural Architecture for Interpretable Machine Learning
Andrew Kiruluta
We propose a novel machine learning architecture that departs from conventional neural network paradigms by leveraging quantum spectral methods, specifically Pade approximants and…
Beyond Neural Networks: Symbolic Reasoning over Wavelet Logic Graph Signals
Andrew Kiruluta, Andreas Lemos, Priscilla Burity
We present a fully non neural learning framework based on Graph Laplacian Wavelet Transforms (GLWT). Unlike traditional architectures that rely on convolutional, recurrent, or atte…
Operator-Based Machine Intelligence: A Hilbert Space Framework for Spectral Learning and Symbolic Reasoning
Andrew Kiruluta, Andreas Lemos, Priscilla Burity
Traditional machine learning models, particularly neural networks, are rooted in finite-dimensional parameter spaces and nonlinear function approximations. This report explores an…
Wavelet Logic Machines: Learning and Reasoning in the Spectral Domain Without Neural Networks
Andrew Kiruluta
We introduce a fully spectral learning framework that eliminates traditional neural layers by operating entirely in the wavelet domain. The model applies learnable nonlinear transf…
Adaptive Two Sided Laplace Transforms: A Learnable, Interpretable, and Scalable Replacement for Self-Attention
Andrew Kiruluta
We propose an innovative, learnable two-sided short-time Laplace transform (STLT) mechanism to supplant the traditional self attention in transformer-based LLMs. Our STLT introduce…
Breaking Quadratic Barriers: A Non-Attention LLM for Ultra-Long Context Horizons
Andrew Kiruluta, Preethi Raju, Priscilla Burity
We present a novel non attention based architecture for large language models (LLMs) that efficiently handles very long context windows, on the order of hundreds of thousands to po…
FourierNAT: A Fourier-Mixing-Based Non-Autoregressive Transformer for Parallel Sequence Generation
Andrew Kiruluta, Eric Lundy, Andreas Lemos
We present FourierNAT, a novel non-autoregressive Transformer (NAT) architecture that employs Fourier-based mixing in the decoder to generate output sequences in parallel. While tr…
Learnable Multi-Scale Wavelet Transformer: A Novel Alternative to Self-Attention
Andrew Kiruluta, Priscilla Burity, Samantha Williams
Transformer architectures, underpinned by the self-attention mechanism, have achieved state-of-the-art results across numerous natural language processing (NLP) tasks by effectivel…
State Fourier Diffusion Language Model (SFDLM): A Scalable, Novel Iterative Approach to Language Modeling
Andrew Kiruluta, Andreas Lemos
In recent years, diffusion based methods have emerged as a powerful paradigm for generative modeling. Although discrete diffusion for natural language processing has been explored…
Unsupervised Machine Learning Hybrid Approach Integrating Linear Programming in Loss Function: A Robust Optimization Technique
Andrew Kiruluta, Andreas Lemos
This paper presents a novel hybrid approach that integrates linear programming (LP) within the loss function of an unsupervised machine learning model. By leveraging the strengths…