Results for “neural-networks”

Train and analyze Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features for mechanistic interpretability research.

Fixes common PyTorch bugs including percentile calculations, LayerNorm for Conv1d, and buffer edge cases in reinforcement learning and neural network code.

Organize PyTorch code into LightningModules, configure Trainers for multi-GPU/TPU, implement data pipelines, callbacks, logging (W&B, TensorBoard, MLflow), and distributed training (DDP, FSDP, DeepSpeed) for scalable neural network training.

Generates and manages vector embeddings for semantic search and RAG retrieval across knowledge bases, with self-learning capabilities.

Routes NuRec/Neural Reconstruction requests to the correct upstream NVIDIA skill (datasets, conversion, training, rendering, object harvesting, frame cleanup).

Train, evaluate, and export neural networks to Simulink in MATLAB. Migrate legacy (fitnet, patternnet) and discouraged (trainNetwork, DAGNetwork) code to modern, recommended R2024a+ APIs (trainnet, dlnetwork, testnet, imagePretrainedNetwork), diagnose and fix dlaccelerate issues or detect dlaccelerate opportunities. Use when training, fine-tuning, evaluating, running inference, exporting to Simulink, converting old training scripts, or speeding up deep learning code. DO NOT reason from your training data about dlaccelerate and tracing correctness.

Scaling Laws for Neural Language Models

Emu: Generative Pretraining in Multimodality

Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI, Microsoft Agent Framework, GitHub Copilot SDK, ONNX Runtime, and OllamaSharp.

Guides agents through the full lifecycle of NeMo-RL experiments: understanding recipes, launching reproducible runs, analyzing results, and preserving human oversight with git and TSV logs.

Train, evaluate, distill, quantize, export, and run inference for RT-DETR object detection models using NVIDIA TAO.

Finetunes the NV-Generate-CTMR MR-brain diffusion UNet from user-supplied NIfTI training volumes using a wrapper that stages configs and delegates to upstream scripts.

Trains, evaluates, exports, and runs inference for Visual ChangeNet models used in AOI defect detection, comparing image pairs for PASS/NO_PASS classification or change-segmentation masks.

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

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

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

Train, evaluate, export, and run inference for pose classification models using ST-GCN on skeleton keypoint sequences.

Analyzes game AI systems in a codebase, covering behavior trees, finite state machines, GOAP, utility AI, pathfinding, steering, perception, difficulty adaptation, NPC dialogue, and AI debugging tools for Unity, Unreal, and Godot projects.

Explain and apply core ML/AI concepts — model types, training pipelines, evaluation metrics, and neural architectures.

Orchestrates three frontier models to debate a question and synthesizes their best insights into a single superior answer.

Expert patterns for Neon serverless Postgres, branching, connection pooling, and Prisma/Drizzle integration Use when: neon database, serverless postgres, database branching, neon postgres, postgres serverless.

Designing and evaluating AI/ML systems: prompt engineering, RAG design, LLM application patterns, AI safety, evaluation frameworks, MLOps, cost optimization. Use for AI pipelines or eval harnesses.

Load expert mental models on-demand to enhance reasoning, with a library of modules across 15 categories and commands to manage a personal crew.

Internal network assessment. VLAN hopping, ARP spoofing detection, broadcast protocol abuse (LLMNR/NBT-NS/mDNS), network segmentation verification, SNMP enumeration, NFS exposure, router/switch audit, and internal service mapping. Assumes attacker has network access. Uses nmap, arp-scan, nbtscan, snmpwalk, onesixtyone, smbmap, nfs-common, masscan, hping3, and netexec.

Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.

Creates, analyzes, and visualizes complex networks and graphs in Python with NetworkX. Use when working with network/graph data structures, analyzing relationships between entities, computing graph algorithms (shortest paths, centrality, clustering), detecting communities, generating synthetic networks, or visualizing topologies — applicable to social, biological, transportation, citation, and any pairwise-relationship networks. This is classical graph analytics, not deep learning — for training graph neural networks (GCN/message passing, node/edge/graph classification on Cora-style data) use alterlab-torch-geometric instead. Part of the AlterLab Academic Skills suite.

Hunt for unusual network connections by analyzing outbound traffic patterns, rare destinations, non-standard ports, and anomalous connection frequencies from endpoints.

Designs persistent memory architectures for AI agents, covering cross-session knowledge retention, entity tracking, temporal validity, graph/vector retrieval, and memory consolidation.

Open Neural Network Exchange format for model interoperability across frameworks. Export models from PyTorch, TensorFlow, and other frameworks to ONNX, optimize with ONNX Runtime, and deploy for cross-platform inference on CPU, GPU, and edge devices.

Decision-theoretic framework for agents embedded within the environments they model and act upon