Parker Bidigare
Community@sovr610 · Detroit Michigan
Welcome! I have been a programmer all my life along side electronic design. Started with C++ and Java back when I was 12 years old. I do C#,python, js and more.
Agent Skills by Parker Bidigare
Showing 48 vetted skills indexed across 1 GitHub repositories.
Paper-to-Spec Compiler
Fetch arXiv papers and compile them into machine-readable spec.yaml artifacts.
Fast Attention Path (PyTorch SDPA + optional FlashAttention-2)
Route PyTorch scaled dot product attention across Flash, Efficient, cuDNN, and Math backends.
Meta-Learning Suite (MAML/FOMAML/Reptile + MAML++ Enhancements)
Execute meta-learning workflows for MAML, FOMAML, Reptile, and MAML++ enhancements.
World Model Architecture Scaffold
Generate a modular world-model scaffold with ABC interfaces and Hydra-compatible YAML configs.
V-JEPA 2 Video & Masking
Orchestrate V-JEPA 2 video tokenization and spatiotemporal masking for pretraining.
Multi-Modal Alignment for Shared Embedding Space
Align encoder outputs from vision, text, audio, and sensor modalities into a shared embedding space.
Neuro-Symbolic Engine (Fuzzy Logic + LTN/Real Logic Grounding)
Ground symbols to neural modules and evaluate fuzzy-logic rules over embeddings.
Data Pipeline & Loaders
Register and consume phase-aware data loaders for brain_ai across 7 training phases.
V-JEPA 2 Vision Transformer
Implement the V-JEPA 2 Vision Transformer architecture for image and video tasks.
Hyperparameter Search
Automate phase-wise hyperparameter optimization for BrainAI training pipelines.
Global Workspace Competition + Broadcast + Working Memory with Ignition Dynamics
Tokenize and fuse multi-modal encoder outputs into a constrained global workspace.
Dual-Process Reasoning (System 1/2 + Metacognitive Control)
Route System 1 predictions and System 2 refinement with deterministic metacognitive control.
BrainAI Spiking Core (LIF Family) + Surrogate Gradient Training
Implement explicit state contracts for LIF-family spiking neurons with surrogate gradients.
Distributed Scaling
Configure DDP and FSDP distributed training for BrainAI models across GPUs and nodes.
BrainAI System Orchestrator
Orchestrates BrainAI modules into deterministic pipelines with explicit contracts and bypass paths.
Video DataLoader Pipeline (Decord + tf.data)
Build configurable video data pipelines with Decord PyTorch and tf.data TPU paths.
Visualization & Interpretability
Render spike rasters, attention heatmaps, and reasoning traces from brain_ai internals.
V-JEPA 2 Data Pipeline
Build and validate a scalable V-JEPA 2 video data pipeline with YAML-config-driven DataLoader construction.
V-JEPA 2 Distributed Training
Distribute V-JEPA 2 training across GPUs and nodes with NCCL and SLURM.
Evaluation & Benchmarks
Evaluate brain_ai models with standardized benchmarks and JSON/CSV reports.
Active Inference Agent (Generative Model + EFE + Empowerment)
Build Active Inference agents that plan actions by minimizing Expected Free Energy.
Task2Vec Task Embeddings + Curriculum/Clustering
Compute Fisher-based Task2Vec embeddings for episodic few-shot tasks and cluster them for curriculum workflows.
Affective State Estimator (Valence-Arousal + Appraisal + Modulation)
Maps cognitive signals to Valence-Arousal-Dominance and outputs modulation targets for AI agents.
DreamerV3-Style RSSM World Model
Build a recurrent state space model with BlockGRU and unimix sampling.