**Neural Architecture Search (NAS)** learns a modular architecture which can be transferred from a small dataset to a large dataset. The method does this by reducing the problem of learning best convolutional architectures to the problem of learning a small convolutional cell. The cell can then be stacked in series to handle larger images and more complex datasets.

Note that this refers to the original method referred to as NAS - there is also a broader category of methods called "neural architecture search".

**Auxiliary Classifiers** are type of architectural component that seek to improve the convergence of very deep networks. They are classifier heads we attach to layers before the end of the network. The motivation is to push useful gradients to the lower layers to make them immediately useful and improve the convergence during training by combatting the vanishing gradient problem. They are notably used in the Inception family of convolutional neural networks.

Auxiliary Classifier

Neural Architecture Search

Learning Transferable Architectures for Scalable Image Recognition

**Double Q-learning** is an off-policy reinforcement learning algorithm that utilises double estimation to counteract overestimation problems with traditional Q-learning. 

The max operator in standard [Q-learning](https://paperswithcode.com/method/q-learning) and [DQN](https://paperswithcode.com/method/dqn) uses the same values both to select and to evaluate an action. This makes it more likely to select overestimated values, resulting in overoptimistic value estimates. To prevent this, we can decouple the selection from the evaluation, which is the idea behind Double Q-learning:

$$ Y^{Q}\_{t} = R\_{t+1} + \gamma{Q}\left(S\_{t+1}, \arg\max\_{a}Q\left(S\_{t+1}, a; \mathbb{\theta}\_{t}\right);\mathbb{\theta}\_{t}\right) $$

The Double Q-learning error can then be written as:

$$ Y^{DoubleQ}\_{t} = R\_{t+1} + \gamma{Q}\left(S\_{t+1}, \arg\max\_{a}Q\left(S\_{t+1}, a; \mathbb{\theta}\_{t}\right);\mathbb{\theta}^{'}\_{t}\right) $$

Here the selection of the action in the $\arg\max$ is still due to the online weights $\theta\_{t}$. But we use a second set of weights $\mathbb{\theta}^{'}\_{t}$ to fairly evaluate the value of this policy.

Source: [Deep Reinforcement Learning with Double Q-learning](https://paperswithcode.com/paper/deep-reinforcement-learning-with-double-q)

Source	Learning Transferable Architectures for Scalable Image Recognition
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com