trainingObjective
P12747
predicate
Indicates the goal or target outcome that a training process is designed to achieve.
All labels observed (13)
| Label | Occurrences |
|---|---|
| trainingObjective canonical | 84 |
| optimizationObjective | 19 |
| trainingGoal | 12 |
| lossFunction | 10 |
| hasTrainingObjective | 8 |
| usesTrainingObjective | 8 |
| pretrainingObjective | 6 |
| learningObjective | 5 |
| trainingTarget | 5 |
| VAEObjective | 1 |
| goalOfTraining | 1 |
| supportsTrainingObjective | 1 |
| trainingCriterion | 1 |
Description generation (PDg)
The one-sentence description above was generated by prompting gpt-5.1 with the predicate name and this instruction.
Instruction
Given a predicate that represents a relationship or action between entities, generate a one-sentence description explaining its meaning. # Instructions Focus on describing the relationship, not the entities themselves. # Response Format Begin the description with \' Indicates...\'
Input
Predicate: trainingObjective
Generated description
Indicates the goal or target outcome that a training process is designed to achieve.
Sample triples (161)
| Subject | Object |
|---|---|
| Boltzmann machines | maximize data log-likelihood ⓘ |
| LeNet | classification accuracy via predicate surface "optimizationObjective" ⓘ |
| LeNet | cross-entropy loss via predicate surface "lossFunction" ⓘ |
| GPT-2 | next token prediction ⓘ |
| GPT-3.5 | next-token prediction ⓘ |
| GPT-3 | next-token prediction ⓘ |
| Oregon State Beavers men’s golf | development of collegiate golfers ⓘ |
| WaveNet | maximum likelihood estimation ⓘ |
| WaveNet | cross-entropy loss over quantized samples ⓘ |
| AlphaZero | maximize expected game outcome via predicate surface "learningObjective" ⓘ |
| MuZero | maximize expected cumulative reward via predicate surface "optimizationObjective" ⓘ |
| Generative Adversarial Networks | adversarial loss via predicate surface "lossFunction" ⓘ |
| AlexNet | cross-entropy loss via predicate surface "lossFunction" ⓘ |
| LogisticRegression | logistic loss minimization with regularization via predicate surface "optimizationObjective" ⓘ |
| A3C | maximize expected cumulative reward via predicate surface "optimizationObjective" ⓘ |
| lua (Hawaiian martial art) | battlefield effectiveness via predicate surface "trainingGoal" ⓘ |
| lua (Hawaiian martial art) | rapid incapacitation of opponents via predicate surface "trainingGoal" ⓘ |
|
WebText dataset
surface form:
WebText
|
next-token prediction ⓘ |
| CLIP | maximize similarity of matching image-text pairs ⓘ |
| CLIP | minimize similarity of non-matching image-text pairs ⓘ |
| CLIP | contrastive loss via predicate surface "lossFunction" ⓘ |
| CLIP | InfoNCE-style loss via predicate surface "lossFunction" ⓘ |
| Transformer | maximum likelihood estimation for sequence modeling ⓘ |
| GPT series | next-token prediction ⓘ |
| European Union Police Mission in Afghanistan | Afghan National Police via predicate surface "trainingTarget" ⓘ |
| European Union Police Mission in Afghanistan | Afghan Ministry of Interior personnel via predicate surface "trainingTarget" ⓘ |
| European Union Police Mission in Afghanistan | Afghan criminal investigation services via predicate surface "trainingTarget" ⓘ |
| Diederik P. Kingma | evidence lower bound via predicate surface "VAEObjective" ⓘ |
| Tai Chi | health improvement via predicate surface "trainingGoal" ⓘ |
| Tai Chi | martial effectiveness via predicate surface "trainingGoal" ⓘ |
| Tai Chi | stress reduction via predicate surface "trainingGoal" ⓘ |
| Tai Chi | spiritual cultivation via predicate surface "trainingGoal" ⓘ |
| WaveRNN | maximum likelihood estimation via predicate surface "hasTrainingObjective" ⓘ |
| WaveRNN | cross-entropy loss on audio samples via predicate surface "hasTrainingObjective" ⓘ |
| WaveGlow | maximum likelihood ⓘ |
| WaveGlow | log-likelihood maximization ⓘ |
| PixelRNN | maximum likelihood estimation ⓘ |
| PixelRNN | log-likelihood maximization ⓘ |
| Parallel WaveNet | match teacher WaveNet distribution ⓘ |
| Fisher's linear discriminant | Rayleigh quotient of scatter matrices via predicate surface "optimizationObjective" ⓘ |
| AlphaGo Zero | maximize probability of winning Go games ⓘ |
| Auto-Encoding Variational Bayes | maximization of ELBO via predicate surface "trainingCriterion" ⓘ |
| Helmholtz machine | maximize data likelihood approximately via predicate surface "hasTrainingObjective" ⓘ |
| Helmholtz machine | minimize divergence between recognition and generative distributions via predicate surface "hasTrainingObjective" ⓘ |
| Distributed Representations of Sentences and Documents | predict words given paragraph vector and context via predicate surface "optimizationObjective" ⓘ |
| Distributed Representations of Sentences and Documents | predict words given paragraph vector alone in DBOW variant via predicate surface "optimizationObjective" ⓘ |
| Show and Tell: A Neural Image Caption Generator | maximize likelihood of correct caption ⓘ |
| Pointer Networks | supervised learning ⓘ |
| Pointer Networks | maximize likelihood of correct index sequence ⓘ |
|
"Principles of Microeconomics"
surface form:
Principles of Microeconomics
|
introduce basic microeconomic concepts via predicate surface "learningObjective" ⓘ |