Difference between revisions of "Learning Techniques"
| Line 12: | Line 12: | ||
| − | <b>Learning Problems:</b> | + | <b>Learning Problems:</b> three main types of learning problems in machine learning |
* [[PRIMO.ai#Supervised|Supervised Learning]] | * [[PRIMO.ai#Supervised|Supervised Learning]] | ||
* [[PRIMO.ai#Unsupervised|Unsupervised Learning]] | * [[PRIMO.ai#Unsupervised|Unsupervised Learning]] | ||
| Line 18: | Line 18: | ||
| − | <b>Hybrid Learning Problems:</b> | + | <b>Hybrid Learning Problems:</b> The lines between unsupervised and supervised learning is blurry, and there are many hybrid approaches that draw from each field of study. |
* [[PRIMO.ai#Semi-Supervised|Semi-Supervised Learning]] | * [[PRIMO.ai#Semi-Supervised|Semi-Supervised Learning]] | ||
* [[PRIMO.ai#Self-Supervised|Self-Supervised Learning]] | * [[PRIMO.ai#Self-Supervised|Self-Supervised Learning]] | ||
| Line 24: | Line 24: | ||
| − | <b>Statistical Inference:</b> | + | <b>Statistical Inference:</b> Inference refers to reaching an outcome or decision. In machine learning, fitting a model and making a prediction are both types of inference. There are different paradigms for inference that may be used as a framework for understanding how some machine learning algorithms work or how some learning problems may be approached. |
| − | Inference refers to reaching an outcome or decision. In machine learning, fitting a model and making a prediction are both types of inference. There are different paradigms for inference that may be used as a framework for understanding how some machine learning algorithms work or how some learning problems may be approached. | ||
* Inductive Learning | * Inductive Learning | ||
* Deductive Inference | * Deductive Inference | ||
Revision as of 13:09, 8 December 2019
YouTube search... ...Google search
- 14 Different Types of Learning in Machine Learning | Jason Brownlee - Machine Learning Mastery
- Natural Language
Learning Problems: three main types of learning problems in machine learning
Hybrid Learning Problems: The lines between unsupervised and supervised learning is blurry, and there are many hybrid approaches that draw from each field of study.
Statistical Inference: Inference refers to reaching an outcome or decision. In machine learning, fitting a model and making a prediction are both types of inference. There are different paradigms for inference that may be used as a framework for understanding how some machine learning algorithms work or how some learning problems may be approached.
- Inductive Learning
- Deductive Inference
- Transductive Learning
Learning Techniques:
- Active Learning
- Online Learning
- Text Transfer Learning
- Image/Video Transfer Learning
- Few Shot Learning
- Transfer Learning a model trained on one task is re-purposed on a second related task
- Ensemble Learning
- Multi-Task Learning (MTL)
- Apprenticeship Learning - Inverse Reinforcement Learning (IRL)
- Imitation Learning
- Simulated Environment Learning
- Lifelong Learning - Catastrophic Forgetting Challenge
