Machine Learning Glossary: Difference between revisions
No edit summary |
No edit summary |
||
| Line 2: | Line 2: | ||
==C== | ==C== | ||
* [[Capsule neural network]] | |||
* [[Convolutional neural network]] or CNN - A neural network architecture for image data, or other data on a regular grid. | * [[Convolutional neural network]] or CNN - A neural network architecture for image data, or other data on a regular grid. | ||
| Line 7: | Line 8: | ||
* Dilation - how spread out a CNN kernel is. See [[Convolutional neural network]]. | * Dilation - how spread out a CNN kernel is. See [[Convolutional neural network]]. | ||
* Domain Adaptation - An area of research focused on making neural network work with alternate domains, or sources of data. | * Domain Adaptation - An area of research focused on making neural network work with alternate domains, or sources of data. | ||
==E== | |||
* Early stopping - a technique where you stop training once the validation loss begins increasing. This is not used very often anymore with large models. | |||
==F== | ==F== | ||
| Line 26: | Line 30: | ||
==N== | ==N== | ||
* Normalized Device Coordinates - In images, pixels are in coordinates of <math>[-1, 1]\times[-1, 1] </math>. | * Normalized Device Coordinates - In images, pixels are in coordinates of <math>[-1, 1]\times[-1, 1] </math>. | ||
==O== | |||
* Overfitting - when a model begins to learn noise specific to your training data, thereby worsening performance on non-training data. | |||
==R== | ==R== | ||
* Recurrent neural network (RNN) - A type of neural network which operates sequentially on sequence data. | * Recurrent neural network (RNN) - A type of neural network which operates sequentially on sequence data. | ||
* [[Reinforcement learning]] - an area of machine learning focused on learning to perform actions, E.g. playing a game | |||
==S== | ==S== | ||
| Line 35: | Line 43: | ||
==T== | ==T== | ||
* [[Transfer Learning]] - Techniques to make a neural network perform a different task than what it is trained on. | * [[Transfer Learning]] - Techniques to make a neural network perform a different task than what it is trained on. | ||
* [[Transformer (machine learning model)]] - A neural network architecture for sequence data. | * [[Transformer (machine learning model)]] - A neural network architecture for sequence data which uses attention between elements of the sequence. | ||
==U== | |||
* Underfitting - when a model performs poorly on both training and validation data, usually due to inadequate model complexity or training duration. | |||
Revision as of 20:08, 23 September 2021
Machine Learning, Computer Vision, and Computer Graphics Glossary
C
- Capsule neural network
- Convolutional neural network or CNN - A neural network architecture for image data, or other data on a regular grid.
D
- Dilation - how spread out a CNN kernel is. See Convolutional neural network.
- Domain Adaptation - An area of research focused on making neural network work with alternate domains, or sources of data.
E
- Early stopping - a technique where you stop training once the validation loss begins increasing. This is not used very often anymore with large models.
F
- Fully connected network - The standard neural network model where each layer is a sequence of nodes.
G
- Generative adversarial network or GAN - A neural network setup for generating examples from a training distribution.
- Graph Neural Network
I
- Intersection over Union - A metric for computing the accuracy of bounding box prediction.
L
- Long short-term memory or LSTM - An RNN neural network architecture which has two sets of hidden states for long and short term.
M
- Multilayer perceptron - See Fully connected network.
N
- Normalized Device Coordinates - In images, pixels are in coordinates of \(\displaystyle [-1, 1]\times[-1, 1] \).
O
- Overfitting - when a model begins to learn noise specific to your training data, thereby worsening performance on non-training data.
R
- Recurrent neural network (RNN) - A type of neural network which operates sequentially on sequence data.
- Reinforcement learning - an area of machine learning focused on learning to perform actions, E.g. playing a game
S
- Stride - how far the CNN kernel in terms of input pixels moves between output pixels.
T
- Transfer Learning - Techniques to make a neural network perform a different task than what it is trained on.
- Transformer (machine learning model) - A neural network architecture for sequence data which uses attention between elements of the sequence.
U
- Underfitting - when a model performs poorly on both training and validation data, usually due to inadequate model complexity or training duration.