From the 3 of 6 linked papers with an AI index.
6 papers
The RG-Flow Transformer: Encoding Scale-Free Dynamics in Scarce EEG
Dibakar Sigdel
The paper introduces the RG-Flow Transformer, a transformer architecture with a renormalization‑group inductive bias designed to capture scale‑free dynamics in EEG, and evaluates i…
PhasorFlow: A Python Library for Unit Circle Based Computing
Dibakar Sigdel, Namuna Panday
PhasorFlow is an open‑source Python library that enables computation on the unit circle using complex phasors and unitary wave‑interference gates, providing a variational phasor ci…
Quantum Port-Hamiltonian Neural Networks: Learning Conservative and Dissipative Dynamics via Measurement-Induced Nonlinearity
Dibakar Sigdel
The paper proposes Quantum Port-Hamiltonian Neural Networks, a family of parameterized quantum circuits that learn classical conservative and dissipative dynamics while preserving…
A Physics-Inspired Classical Digital Twin of Cortical Dynamics: A Band-Stratified Metriplectic Port-Hamiltonian Neural Network Learned from Brain-Computer-Interface EEG
Dibakar Sigdel
We present a physics-inspired classical digital twin of brain-computer- interface (BCI) data: a graph neural network constrained to a band-stratified, metriplectic port-Hamiltonian…
Variational Phasor Circuits for Phase-Native Brain-Computer Interface Classification
Dibakar Sigdel
We present the Variational Phasor Circuit (VPC), a deterministic classical learning architecture on the continuous unit-circle manifold. Inspired by variational quantum circu…
The Phasor Transformer: Resolving Attention Bottlenecks on the Unit Circle
Dibakar Sigdel
Transformer models have redefined sequence learning, yet dot-product self-attention introduces a quadratic token-mixing bottleneck for long-context time-series. We introduce the Ph…