trainingMethod
P16019
predicate
Indicates the specific approach, technique, or procedure used to train an entity (such as a person, model, or system).
Aliases (11)
- trainedWith ×7
- trainingStyle ×4
- usesTrainingMethod ×4
- trainingMethods ×3
- trainingMode ×3
- learningAlgorithm ×2
- trainingSignal ×2
- fineTuningMethod ×1
- learningType ×1
- trainingAlgorithm ×1
- trainingTechnique ×1
Sample triples (62)
| Subject | Object |
|---|---|
| A fast learning algorithm for deep belief nets | backpropagation ("fineTuningMethod") → |
| A fast learning algorithm for deep belief nets | probabilistic generative learning ("learningType") → |
| A2C | temporal-difference error ("trainingSignal") → |
| Academic art | atelier system → |
| Academic art | copying old masters → |
| Academic art | hierarchical curriculum → |
| Academic art | rigorous entrance examinations → |
| AlexNet | stochastic gradient descent with momentum ("trainingTechnique") → |
| AlphaGo | reinforcement learning through self-play → |
| AlphaGo | supervised learning from human expert games → |
| AlphaStar | league-based training → |
| AlphaStar | reinforcement learning via self-play → |
| AlphaStar | supervised learning from human replays → |
| AlphaZero | self‑play → |
| Atari deep Q-network | game score reward ("trainingSignal") → |
| Brazilian jiu-jitsu | drilling techniques ("trainingMethods") → |
| Brazilian jiu-jitsu | live rolling ("trainingMethods") → |
| Brazilian jiu-jitsu | sparring ("trainingMethods") → |
| ChatGPT | reinforcement learning from human feedback → |
| ChatGPT | supervised fine-tuning → |
| ChatGPT | unsupervised learning → |
| Civil Services Academy Lahore | classroom instruction ("trainingMode") → |
| Civil Services Academy Lahore | field visits ("trainingMode") → |
| Civil Services Academy Lahore | simulations and exercises ("trainingMode") → |
| DistBelief | stochastic gradient descent ("trainingAlgorithm") → |
| GPT-4 | reinforcement learning from human feedback → |
| GPT-4 | supervised fine-tuning → |
| GPT-4 | unsupervised pre-training → |
| Gradient-based learning applied to document recognition | backpropagation of gradients ("learningAlgorithm") → |
| Gradient-based learning applied to document recognition | stochastic gradient descent ("learningAlgorithm") → |
| Hogan’s Alley (FBI training facility) | force-on-force simulations → |
| Hogan’s Alley (FBI training facility) | interactive judgmental shooting exercises → |
| Hogan’s Alley (FBI training facility) | live-action exercises → |
| Hogan’s Alley (FBI training facility) | role-playing scenarios → |
| Imperial Russian Ballet | Vaganova method → |
| Károly Takács | secretly practiced left-handed shooting for years after injury → |
| LeNet | stochastic gradient descent → |
| LeNet | supervised learning → |
| Mariinsky Ballet | Vaganova method → |
| Michael Phelps | North Baltimore Aquatic Club ("trainedWith") → |
| MuZero | reinforcement learning → |
| MuZero | self-play → |
| Neutral Buoyancy Laboratory | neutral buoyancy → |
| Organized Reserve Corps | part-time training → |
| Organized Reserve Corps | peacetime drills and instruction → |
| PPO | mini-batch updates ("trainingStyle") → |
| PPO | multiple epochs over collected trajectories ("trainingStyle") → |
| ResNet | stochastic gradient descent → |
| Suhrawardiyya | graded stages of initiation → |
| Suhrawardiyya | systematic spiritual instruction → |
| The Basic School | classroom instruction ("usesTrainingMethod") → |
| The Basic School | field exercises ("usesTrainingMethod") → |
| The Basic School | leadership reaction exercises ("usesTrainingMethod") → |
| The Basic School | live-fire training ("usesTrainingMethod") → |
| UK Cadet Forces | progressive qualification system ("trainingStyle") → |
| UK Cadet Forces | structured syllabus-based training ("trainingStyle") → |
| deep feedforward networks | backpropagation ("trainedWith") → |
| deep feedforward networks | gradient descent ("trainedWith") → |
| deep feedforward networks | mini-batch gradient descent ("trainedWith") → |
| deep feedforward networks | stochastic gradient descent ("trainedWith") → |
| variational autoencoders | backpropagation ("trainedWith") → |
| variational autoencoders | stochastic gradient descent ("trainedWith") → |