'deep' 검색 결과

Treinar modelos de Mixture of Experts (MoE) usando DeepSpeed ou HuggingFace. Use ao treinar modelos em larga escala com computação limitada (redução de 5× em custos vs modelos densos), implementar arquiteturas esparsas como Mixtral 8x7B ou DeepSeek-V3, ou escalar capacidade de modelo sem aumento proporcional de computação. Cobre arquiteturas MoE, mecanismos de roteamento, balanceamento de carga, paralelismo de especialistas e otimização de inferência.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models. Supports batch analysis of audio files, generates confidence scores, and produces forensic reports. Activates for requests involving deepfake voice detection, vishing investigation, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Cursorでユーザーとの対話を通じて要件や設計の選択肢を整理し、実装前の決定事項を確定する。曖昧な要件や複数案のどれを採るかをユーザーと決める場合に使う。独立した熟考は deepthink、計画作成は deepplan。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

ユーザーとの対話で要件や設計の選択肢を整理し、実装前の決定事項を確定する。曖昧な要件や複数案のどれを採るかをユーザーと決める場合に使う。独立した熟考は deepthink、計画作成は deepplan。

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Deepsource — deepSource code analysis management. Covers automated code reviews, issue detection, antipattern analysis, coverage tracking, and analyzer configuration. Use when managing DeepSource projects, reviewing detected issues, configuring analyzers, or tracking code health metrics.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Confluence Deep — deep Confluence management covering spaces, pages, content analytics, permissions, and workspace health. Use when performing deep audits of Confluence usage, analyzing content freshness, reviewing space permissions, or assessing documentation coverage across an Atlassian Confluence instance.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Aws Dynamodb Deep — aWS DynamoDB deep-dive management covering table configurations, capacity analysis, GSI/LSI health, auto-scaling policies, streams, backups, contributor insights, and TTL settings. Use when performing deep analysis of DynamoDB tables, optimizing capacity and throughput, debugging throttling, or auditing table configurations beyond basic inventory.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Use when working with Azure Boards Deep — deep Azure Boards management covering work items, sprints, backlogs, queries, and team velocity analytics. Use when performing deep audits of Azure DevOps Boards, analyzing sprint health, reviewing backlog grooming, or assessing team capacity and velocity across Azure DevOps projects.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

NVIDIA DeepStream model-import guidance for bringing vision models from Hugging Face or NVIDIA NGC into DeepStream pipelines with export, TensorRT build, and benchmark steps.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models. Supports batch analysis of audio files, generates confidence scores, and produces forensic reports. Activates for requests involving deepfake voice detection, vishing investigation, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Train neural operators (FNO, DeepONet) to learn solution maps for parametric PDE families. Once trained, solve new PDE instances in milliseconds. Use when you need to solve many instances of the same PDE with different parameters/ICs/BCs.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Predict RBP binding from RNA sequence using deep learning models (RBPNet sequence-to-signal, RNAProt RNN, GraphProt2 GCN with structure, DeepCLIP, DeepRiPe multi-modal CNN) for variant-effect prediction, in silico binding-site discovery, model interpretation, and transfer learning from CLIP and RBNS datasets. Use when computational prediction of RBP binding from sequence is needed, evaluating variant effects on binding without further wet-lab experiments, comparing model performance, or training a custom model on ENCODE eCLIP data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Predict RBP binding from RNA sequence using deep learning models (RBPNet sequence-to-signal, RNAProt RNN, GraphProt2 GCN with structure, DeepCLIP, DeepRiPe multi-modal CNN) for variant-effect prediction, in silico binding-site discovery, model interpretation, and transfer learning from CLIP and RBNS datasets. Use when computational prediction of RBP binding from sequence is needed, evaluating variant effects on binding without further wet-lab experiments, comparing model performance, or training a custom model on ENCODE eCLIP data.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Tests and exploits deep link (URL scheme and App Link) vulnerabilities in Android and iOS mobile applications to identify unauthorized access, data injection, intent hijacking, and redirect manipulation. Use when assessing mobile app attack surface through custom URI schemes, Android App Links, iOS Universal Links, or intent-based navigation. Activates for requests involving deep link security testing, URL scheme exploitation, mobile intent abuse, or link hijacking.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

Detects AI-generated deepfake audio used in voice phishing (vishing) attacks by extracting spectral features (MFCC, spectral centroid, spectral contrast, zero-crossing rate) and classifying samples with machine learning models. Supports batch analysis of audio files, generates confidence scores, and produces forensic reports. Activates for requests involving deepfake voice detection, vishing investigation, AI-generated speech analysis, voice cloning detection, or audio authenticity verification.

한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.

조사 주제를 여러 질문으로 나누고 웹 검색과 본문 검토를 진행합니다. 출처, 확신 수준, 정보 부족 부분을 밝힌 보고서로 정리합니다.

• 경쟁사와 시장 동향 조사
• 도입 전 기술 비교
• 시장 규모와 성장 전망 조사

Research a question from five search angles, gather sources, and test their claims through multiple verification judgments. The workflow combines overlapping findings and produces a cited report with conclusions ranked by confidence.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Investigating a topic from several perspectives
• Checking claims across multiple web sources
• Preparing a research report with citations

Support decisions with market, technical, competitor, and other research. Draft prompts for external research tools, condense existing reports into source-cited summaries, or conduct web research directly, including comparisons between candidates.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Researching markets or competitors for a decision
• Drafting a prompt for an external research tool
• Turning an existing report into a source-cited summary

Develop a research question, search and verify literature, and combine findings into an academic report. Modes also support guided research discussions, claim checking, paper comparisons, and systematic reviews with optional meta-analysis, which statistically combines study results.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Clarify a research direction through guided questions
• Search literature and compare findings across sources
• Check specific claims against supporting sources

Organize PyTorch models and data pipelines with PyTorch Lightning, automate training, save checkpoints, and track experiments. Includes templates and guidance for configuring training across multiple GPUs or TPUs.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Restructure PyTorch training code into LightningModules
• Build reusable data preparation and loading pipelines
• Configure checkpoints, early stopping, and experiment logs

Process next-generation sequencing data with deepTools: convert alignment files into coverage tracks, normalize signals, compare samples, and check quality. Create heatmaps and profiles around genes or peak regions for ChIP-seq, RNA-seq, and ATAC-seq experiments.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Converting BAM files to normalized bigWig tracks
• Checking sequencing quality and replicate agreement
• Plotting heatmaps around transcription start sites

Audit a Python pytest suite for missed faults, uncovered code, slow tests, and unstable results. Deeper checks deliberately alter code to measure detection, while proposed test removals receive separate validation. The skill reports findings without changing tests.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Find gaps in a pytest suite's fault detection
• Investigate slow tests and setup costs
• Identify intermittent or order-dependent failures

Take an idea or issue through requirements clarification, reviewed planning, implementation, and verification. Supervise all stages in one recoverable OMX workflow, preserving artifacts and progress so work can resume or return to planning when findings require changes.

한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.

• Deliver an issue from requirements clarification through verification
• Turn an initial idea into a reviewed implementation plan
• Resume interrupted work from its saved phase