6

Self-supervised learning is when you use some parts of the samples as labels for a task that requires a good degree of comprehension to be solved. I'll emphasize these two key points, before giving an example: Labels are extracted from the sample, so they can be generated automatically, with some very simple algorithm (maybe just random selection). The task ...


5

Note: you mentioned in the comments that you are reading the old, pre-print version of the paper describing AlphaZero on arXiv. My answer will be for the "official", peer-reviewed, more recent publication in Science (which nbro linked to in his comment). I'm not only focusing on the official version of the paper just because it is official, but also because ...


4

The previous answer has given a good insight into the difference between two areas. I would like to give more examples. Semi-Supervised Learning work with improving the data set by adding up new examples. There are iterative systems where we train a model on a given dataset and improve the model further after deploying it on the real world by adding ...


4

So in a sense you are correct. Using your jargon: linear regression will only "work" if the true function is approximately $y=h(x)=\beta^{T}x+\beta_0$. Advantages to using this is that its light, its convex, and all-around easy. but for alot of larger problems, this wont work. As you said you want the machine to do the work, so this is (kinda) where deeper ...


3

Supervised learning The supervised learning (SL) problem is formulated as follows. You are given a dataset $\mathcal{D} = \{(x_i, y_i)_{i=1}^N$, which is assumed to be drawn i.i.d. from an unknown joint probability distribution $p(x, y)$, where $x_i$ represents the $i$th input and $y_i$ is the corresponding label. You choose a loss function $\mathcal{L}: ...


3

The programmer already guides the RL algorithm (or agent) by specifying the reward function. However, the reward function alone may not be sufficient to learn efficiently and fast, as you correctly noticed. To attempt to solve this inefficiency problem, one solution is to combine reinforcement learning with supervised learning. For example, the paper Deep Q-...


3

Both semi-supervised and self-supervised methods are similar in the sense that the goal is to learn with fewer labels per class. The way both formulate this is quite different: Self-Supervised Learning: This line of work aims to learn image representations without requiring human-annotated labels and then use those learned representations on some ...


3

If you learn a policy or a value function from experience (that is, interaction with an environment), that's RL. In the case of AlphaGo, the MCTS is used to acquire the experience. RL could in fact be considered supervised learning (SL) or, more specifically, self-supervised learning, where the experience corresponds to the labels in SL, especially nowadays ...


3

Any supervised learning problem can be cast as an equivalent reinforcement learning one. Suppose you have the training dataset $\mathcal{D} = \{ (x_i, y_i \}_{i=1}^N$, where $x_i$ is an observation and $y_i$ the corresponding label. Then let $x_i$ be a state and let $f(x_i) = \hat{y}_i$, where $f$ is your (current) model, be an action. So, the predicted ...


3

Automated machine learning (AutoML) is an umbrella term that encompasses a collection of techniques (such as hyper-parameter optimization or automated feature engineering) to automate the design and application of machine learning algorithms and models. Reinforcement learning (RL) is a sub-field of machine learning concerned with the task of making ...


2

Decision Tree learners, on their own, are not a good way to deal with imbalanced data. The most commonly used algorithms, by default, make no attempt to address this problem. If you look carefully at the three sources you post, you will find that they actually all agree on this point. Two of the sources actually propose methods of addressing this ...


2

The paper Fair and Unbiased Algorithmic Decision Making: Current State and Future Challenges argues that ensuring fairness is not a trivial task and that the current statistical formalizations of fairness lead to a long list of criteria that are each flawed (or even harmful) in different contexts, that is, there are trade-offs between the proposed ...


2

RL can be used in the context of Neural Architecture Search (NAS), with is a form of automated ML. A model searches for an architecture that performs a given task. How well this task is performed guides how the architecture will be modified (improved) on the next pass. It works but is very computation-intensive (think hundreds of GPUs). See for instance: B....


2

In Supervised learning, the goal is to learn a mapping from points in a feature space to labels. So that for any new input data point, we are able to predict its label. whereas in Unsupervised learning data set is composed only of points in a feature space, i.e. there are no labels & here the goal is to learn some inner structure or organization in the ...


2

It's perfectly reasonable to apply 'traditional' Deep Learning approaches to try and learn an adjacency matrix (a matrix is just a vector of vectors, which can be flattened into a single output vector) but you might need a lot of training data as N gets larger. Your outputs could certainly have the form of an adjacency matrix, as you describe. Whether it's ...


2

This is the definition of conditional probability + Total probability decomposition formula: $p(y|x) = \frac{p(y,x}{p(x)} = \frac{p(x,y)}{\sum_{y'}p(x,y')}$. The idea is to use some unsupervised learning algorithm to learn the distribution $p(x,y)$ for every possible value of $y$, and by using the previous formula you can find $p(y|x)$.


2

Here are two very related interesting papers: Learning from Human Preferences Improving Reinforcement Learning with Human Input


2

By "immediate vector-valued feedback", they probably mean exactly the label in the "labeled examples" you mentioned.


1

Not familiar with RBF but when you have a small data set image augmentation can help. You can do this easily with the Keras ImageDataGenerator, documentation is here. Alternatively you can create image augmentation yourself using image processing models like PIL or CV2.


1

This formulation can indeed be misleading, as the output of a neural network is usually deterministic (i.e. given the same input $x$, the output is always the same, so there is no sampling), and there isn't really a probability distribution that models any uncertainty associated with the parameters of the network or the input. People often use this ...


1

Sorry for the delay. The term "vector-valued feedback" is compared to scalar-valued feedback. The implication (which I should have made explicit) is that, because vector-valued feedback tells the network the correct answer, the changes in weights required to improve performance are reasonably easy to calculate (e.g. using backprop). In contrast, if a ...


1

For the vast majority of cases where you have a dynamic(and assumed non-linear) relationship between your input and output, you would not use modified architecture. You would simply retrain on the new data. In some cases, based on domain knowledge or intuition, one might put a "weight" on the new data to increase or decrease its importance relative to ...


1

To know if your model needs more training data, try to plot out "learning curves", that are based on increasing size of the training set. Basically, you calculate training and validation accuracy metrics for 1, 2, 3, 4, 5, ..., m training samples. Size of validation set may be constant over time. If the accuracy is still rising when your data set is fully ...


1

The layout problem is suitable for a rule-based approach, as used to generate levels in Rogue or customised home-layouts, you encode some constraints and search the remaining space. The colour problem is also suitable for a rule-based approach, colour is a 3-dimensional space (4 if you include opacity). A palette can be created through taking colours at ...


1

If you see the use case, on higher level it seems to generate some visual output - the design but when seen at lower level, this design is output of some code. One way we can do it is to train a neural network that learns to generate code which can be seen as some form of organized text. So now can be treated as a text generation problem on which you can ...


1

If you look at the theory of CNN, the no.of channels in the input layer is also a parameter that user can decide. In fact, if you are working on monochrome (black & white) images, you have to use only one channel in the input layer. All the libraries should provide a way to design an input layer with no. of channels as an option. But, if you are trying ...


1

The libraries should allow you to specify the number of input channels of the convolutional layer, so no one should prevent you from passing 1-channel images as input to a CNN. For example, in PyTorch, you can specify the number of input channels of the Conv2d object. If your library does not provide such feature, you could convert your 1-channel images to ...


1

Actually regression comes under the statistical analysis. As you know many business activity(decision making) relies in the previous trends that can be grabbed from the organizations transaction data. When regression is performed on those organizational data. One can understand what decision can be made. One could even simulate the different conditions when ...


Only top voted, non community-wiki answers of a minimum length are eligible