Difference between revisions of "Meta-Learning"
m |
|||
| (3 intermediate revisions by the same user not shown) | |||
| Line 15: | Line 15: | ||
http://miro.medium.com/max/544/1*Np91zhHmTqZ4d4j3rwaNvQ.png | http://miro.medium.com/max/544/1*Np91zhHmTqZ4d4j3rwaNvQ.png | ||
| + | |||
| + | Outer Training Methods - | ||
| + | * Black box | ||
| + | ** Random search | ||
| + | *** [[Algorithm Administration#Hyperparameter|Hyperparameter]] optimization | ||
| + | ** [[Reinforcement Learning (RL)]] | ||
| + | ** [[Evolutionary Computation / Genetic Algorithms | Evolution]] | ||
| + | * [[Gradient Descent Optimization & Challenges | Gradients]] - the whole training process is differentiable; 'unroll optimization, compute gradients, then [[Average-Stochastic Gradient Descent (SGD) Weight-Dropped LSTM (AWD-LSTM) | SGD]]. | ||
| + | |||
<youtube>x-mzS5omvFQ</youtube> | <youtube>x-mzS5omvFQ</youtube> | ||
<youtube>lz0ekIVfoFs</youtube> | <youtube>lz0ekIVfoFs</youtube> | ||
<youtube>kmbPnsgHxz4</youtube> | <youtube>kmbPnsgHxz4</youtube> | ||
| − | <youtube> | + | <youtube>ByeRnmHJ-uk</youtube> |
<youtube>wT45v8sIMDM</youtube> | <youtube>wT45v8sIMDM</youtube> | ||
<youtube>SRT0QQ5JS3E</youtube> | <youtube>SRT0QQ5JS3E</youtube> | ||
| + | <youtube>2z0ofe2lpz4</youtube> | ||
Latest revision as of 15:35, 27 September 2020
YouTube search... ...Google search
- Learning Techniques
- Meta-Learning Update Rules for Unsupervised Representation Learning | Luke Metz, Niru Maheswaranathan, Brian Cheung, Jascha Sohl-Dickstein
- From zero to research — An introduction to Meta-learning | Thomas Wolf - Medium
“learning how to learn”... the use of machine learning algorithms to assist in the training and optimization of other machine learning models. What is Meta-Learning? | Daniel Nelson - Unite.ai
Outer Training Methods -
- Black box
- Random search
- Hyperparameter optimization
- Reinforcement Learning (RL)
- Evolution
- Random search
- Gradients - the whole training process is differentiable; 'unroll optimization, compute gradients, then SGD.
