发现data science & ml类别的 Claude 技能。浏览 61 个技能,找到适合您 AI 工作流程的完美功能。
Deploys trained Reinforcement Learning (RL) policies to real robots using high-performance Rust and ONNX Runtime.
Empowers AI agents with adaptive learning and meta-cognitive capabilities to optimize strategies based on past experiences.
Provides hardware specifications, MuJoCo MJCF models, and deployment workflows for the K-Scale flagship humanoid robot platform.
Provides a unified framework for humanoid robot development, reinforcement learning training, and sim-to-real deployment.
Trains and deploys complex neural networks across distributed E2B sandbox environments using the Flow Nexus framework.
Optimizes interaction sequences using information theory and active inference to maximize learning efficiency and information gain.
Synthesizes Patrick Kenny's active inference framework with K-Scale's JAX/MuJoCo robotics stack for advanced predictive coding in robot locomotion.
Implements advanced vector database capabilities for distributed AI systems, multi-agent coordination, and high-performance hybrid search.
Manages persistent memory and pattern learning for AI agents using high-performance vector storage and context synthesis.
Trains humanoid locomotion and manipulation policies using JAX-accelerated MuJoCo simulations and advanced RL algorithms.
Implements high-performance adaptive learning and memory distillation for AI agents using the AgentDB vector backend.
Builds and simulates a cost-efficient, wobbling robot that composes nonstandard musical scales through duck-like vocalizations.
Converts URDF robot descriptions into MJCF format for high-performance MuJoCo and MJX physics simulations.
Standardizes robotics datasets and deploys edge-optimized vision-language-action models for embodied AI applications.
Streamlines the development of data processing pipelines, ABAP integrations, and machine learning scenarios within SAP Data Intelligence Cloud.
Balances algorithmic complexity with exploratory game theory to optimize proof discovery and extract World Extractable Value (WEV).
Composes complex dynamical systems and resource sharers using categorical colimits and operad algebra.
Orchestrates complex world-state transformations using categorical rewriting, graph grafting, and formal semantic verification.
Streamlines the creation, management, and serving of scalable feature stores within the Databricks MLOps ecosystem.
Applies category theory and sheaves on tree decompositions to solve complex combinatorial problems with Fixed-Parameter Tractable (FPT) algorithms.
Optimizes machine learning workflows on Databricks by implementing structured MLflow experiment tracking and model governance patterns.
Conducts rigorous evaluations of claims, evidence, and logical arguments to detect bias and validate research methodologies.
Implements automated model monitoring, drift detection, and performance tracking for production machine learning systems on Databricks.
Orchestrates multi-agent AI swarms for parallel task execution and dynamic coordination using the agentic-flow framework.
Optimizes multi-turn AI conversations by reducing token usage through advanced summarization and context management techniques.
Build and manage declarative, self-healing data pipelines with built-in quality enforcement and automated lineage tracking.
Implements a self-adaptive machine learning retraining framework for automated trading signals and market regime detection.
Evaluates methodological quality and potential bias in research studies using standardized frameworks like RoB 2 and ROBINS-I.
Implements high-performance adaptive learning and experience replay for AI agents using AgentDB's ultra-fast vector storage.
Evaluates the robustness of research findings by testing how results change under different analytical assumptions and data conditions.
Scroll for more results...