Results for “computational-modeling”

Train, evaluate, distill, quantize, export, and run inference for PyTorch-based TAO image classification models with support for multiple backbones.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Big Data Based Modeling Skill

Pixtral 12B: A Frontier Multimodal Model

ML pipeline design — data versioning, experiment tracking, deployment patterns, drift monitoring. Use when building an ML pipeline from data to deployment, setting up MLOps tooling (DVC, MLflow, model registry), choosing deployment patterns (shadow, canary, A/B), or designing monitoring for drift and degradation.

Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.

TRAK: Attributing Model Behavior at Scale

Build 3-scenario financial models (Base/Bull/Bear) for startups with templates by business model, unit economics, cohort analysis, and runway calculations.

Recommend the right AI model for a task by scoring candidates across six dimensions (Reasoning, Engineering, Speed, Breadth, Reliability, Governance) and displaying a spider-chart profile.

Advanced Optics Modeling Skill

Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems.

Acoustics Based Modeling Skill

Train, evaluate, export, and run inference for Masked Auto-Encoder (MAE) models for self-supervised pretraining and fine-tuning of visual representations.

Trains, evaluates, exports, and runs inference for person re-identification models using TAO, learning discriminative embeddings for cross-camera matching.

Import object detection models from HuggingFace or NVIDIA NGC into a DeepStream pipeline with automated ONNX download, TensorRT engine build, custom parser, multi-stream benchmark, and PDF report generation.

Train, evaluate, export, quantize, and run inference on Mask2Former models for panoptic, instance, and semantic segmentation using NVIDIA TAO.

Applied Optics Modeling Skill

Scaling Data-Constrained Language Models

Bayesian modeling with PyMC. Build hierarchical models, MCMC (NUTS), variational inference, LOO/WAIC comparison, posterior checks, for probabilistic programming and inference.

Chameleon: Mixed-Modal Early-Fusion Foundation Models

Matryoshka Representation Learning

Turns model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Conduct structured threat modeling for software systems using established methodologies to identify, prioritize, and mitigate security threats before they are exploited. Use when the user requests threat modeling or provides relevant inputs for this workflow.

Influence Functions in Deep Learning

Applied Logic Modeling Skill

Constraint-based metabolic modeling (COBRA). FBA, FVA, gene knockouts, flux sampling, SBML models, for systems biology and metabolic engineering analysis.

Turn model work into a production ML system with data contracts, reproducible training, quality gates, deployable artifacts, and monitoring.

Expert guidance for distributed NoSQL databases (Cassandra, DynamoDB). Focuses on mental models, query-first modeling, single-table design, and avoiding hot partitions in high-scale systems.

Conversational Pattern Restoration — Fix flat, robotic AI responses across any model and any personality. Restore YOUR natural conversational texture without triggering hype drift. Universal framework tested on 8+ models (Claude, GPT-4o, Grok, Gemini).

Model interpretability and explainability using SHAP (SHapley Additive exPlanations). Use this skill when explaining machine learning model predictions, computing feature importance, generating SHAP plots (waterfall, beeswarm, bar, scatter, force, heatmap), debugging models, analyzing model bias or fairness, comparing models, or implementing explainable AI. Works with tree-based models (XGBoost, LightGBM, Random Forest), deep learning (TensorFlow, PyTorch), linear models, and any black-box model.

Loads and processes whole-slide pathology images, builds spatial graphs, trains deep learning models, and analyzes multiplexed immunofluorescence data across 160+ slide formats.

Every metric encodes an opinion about which mistake hurts.

COCO: Microsoft COCO: Common Objects in Context

Run computational biology tools for protein structure prediction, design, docking, and molecular dynamics on managed cloud GPUs via REST API or MCP server.

Build financial projections, P&L statements, DCF models, and valuation analyses from assumptions and historical data. Use when the user requests financial modeling or provides relevant inputs for this workflow.