<- Back to all tags

Tactic(s) tagged with "machine-learning"

• Apply Cloud Fog Network Architecture (AT)
• Apply Sampling Techniques (AT)
• Choose a Lightweight Algorithm Alternative (AT)
• Choose an Energy Efficient Algorithm (AT)
• Consider Energy-Aware Pruning (AT)
• Consider Federated Learning (AT)
• Consider Graph Substitution (AT)
• Consider Knowledge Distillation (AT)
• Consider Reinforcement Learning for Energy Efficiency (AT)
• Consider Transfer Learning (AT)
• Decrease Model Complexity (AT)
• Design for Memory Constraints (AT)
• Enhance Model Sparsity (AT)
• Minimize Referencing to Data (AT)
• Monitor Computing Power (AT)
• Reduce Number of Data Features (AT)
• Remove Redundant Data (AT)
• Retrain the Model If Needed (AT)
• Set Energy Consumption as a Model Constraint (AT)
• Use Built-In Library Functions (AT)
• Use Checkpoints During Training (AT)
• Use Computation Partitioning (AT)
• Use Data Projection (AT)
• Use Dynamic Parameter Adaptation (AT)
• Use Energy-Aware Scheduling (AT)
• Use Energy-Efficient Hardware (AT)
• Use Informed Adaptation (AT)
• Use Input Quantization (AT)
• Use Power Capping (AT)
• Use Quantization-Aware Training (AT)
• Choose an energy efficient drift detection algorithm (SP)
• [Using Adaptive Response for Sustainable LLM Inference] (AT)
• [Using Energy-Efficient Multi-Objective Optimization for AI Training and Inference] (AT)
• [Using Storage Optimization for Efficient LLM Inference] (AT)
• Limit Ensemble Size (AT)
• RAG Context Caching (AT)
• RAG Context Filtering and Compression (AT)
• Use Majority Voting (AT)
• Adaptive Ensemble (AT)
• Detection Based Model Reconstruction (AT)
• Detection Based Model Repository (AT)
• Energy Efficient Hardware (AT)