Computational NeuroEngineering Lab

CNEL projects

Voltage imaging, biological time-series modeling, and experiment infrastructure connected to CNEL research at UF.

Diagram of Kernel Adaptive Memory: a sequence feeds radial context attention and learned persistent supports before a residual readout and optional online NLMS adaptation.
Research · sequence modeling · adaptive memory

Kernel Adaptive Memory: a transformer alternative for sequence modeling

A proposal for a transformer alternative: use a learned radial geometry for local context, a finite bank of persistent supports for reusable structure, and a lightweight online readout for adaptation after distribution shift.

Radial kernel attentionPersistent memory supportsTransformer comparisonOnline NLMS adaptation
Open project
Diagram of a hierarchical dynamical system: noisy observed signals generate compact latent trajectories used by a classifier.
Research · dynamical systems · classification

Latent-signal classification with hierarchical dynamical systems

Pipeline that maps noisy multichannel time-series observations to compact latent trajectories with a Hierarchical Linear Dynamical System (HLDS), then evaluates those trajectories for classification, separability, and stability.

Hierarchical Linear Dynamical System (HLDS)Latent-signal classificationTemporal representation learning
Open project
Frame from a zebrafish neural imaging video.
Research · neural imaging · signal separation

Zebrafish neural imaging: event detection & source separation

Research platform for zebrafish neural-imaging video: statistical event detection for voltage recordings and a calcium-imaging experiment program that separates activity from background, artifacts, and noise.

Voltage & calcium imagingEvent detectionSource separationStatistical detection
Open project
Plot representing adaptive filtering / time-series modeling.
Research tools · ML infra · reproducibility

Time-series ML experiment library

Reusable experiment scaffolding for time-series ML: standardized configs, runs, metrics, and plots so model comparisons are fair and repeatable.

Time-series modelingExperiment trackingGPU acceleration
Open project
Diagram of spike trains feeding a KLMS decoder that reconstructs a micro-stimulation signal.
Research · neural decoding · reproduction

Spike-train decoding with kernel least-mean-squares (KLMS)

A faithful Python reproduction of Li et al. (IEEE MLSP 2011): a spike-time RKHS KLMS decoder that maps spike trains to micro-stimulation, benchmarked against binned KLMS and GLM baselines.

Kernel adaptive filteringNeural decodingPaper reproduction
Open project