14

Self-supervised learning (or self-supervision) is a relatively recent learning technique (in machine learning) where the training data is autonomously (or automatically) labelled. It is still supervised learning, but the datasets do not need to be manually labelled by a human, but they can e.g. be labelled by finding and exploiting the relations (or ...


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 way children learn is in many ways supervised. It is true that certain abilities are there genetically (visual system, object recognition, to large extent voice recognition), but a lot of human experience is gained as a result of response, either from the environment or from the mentor (parent, teacher, etc). Social interaction is possible only when a ...


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

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 ...


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

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 ...


2

Self-supervised visual recognition is often applied to representation learning. Here we first learn features on unlabeled data (representation learning), and then learn the real model on features extracted from the labeled data. This especially makes sense when we have a lot of unlabeled data and few labeled data. The features can be learned by solving so ...


2

The GA will require a fitness function, which means you need labeled data for comparison. That conclusion is wrong. Yes, sometimes your fitness function will use labeled data. For example, if you want to train an XOR gate or any other known function. However, there is arguably no advantage of training a function with neuroevolution versus backpropagation, ...


2

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 ...


2

Semi-supervised learning is a combination of supervised and unsupervised learning. In semi-supervised learning, there are two datasets: a labelled one and an unlabelled one. There are two main problems that can be solved using semi-supervised learning: transductive learning and inductive learning (generalisation). In the case of transductive learning, the ...


2

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 ...


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

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


2

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 ...


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

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 ...


1

For such time-series data that has a significant amount of periodicity, I would recommend converting data to the frequency domain and performing various spectral analysis methods as @firion has already mentioned. For example, you could perform Fourier Analysis and study the individual components and identify patterns there. Also, it generally not ...


1

I have not worked on this but I think I can give you a theoretical perspective of using VAE's. Regression is a Supervised Learning task and is basically a mapping from Input to Output where the Neural Net will approximate the function $f(input) = output$. VAE's on the other hand are good for finding how a latent variable affects the output. For example, if ...


1

It’s not an exhaustive answer to your question, but here some aspects that might be helpful: A common problem in supervised learning where you will see KL-divergence used are classification tasks. Very often in those cases the data points in the training set are assumed to belong to a single class $c_i$ where $i$ is from some index set $I$. The class ...


1

For this particular classification problem, I would recommend you using a softmax function whose output range is [0,1]. The sum of all outputs should be 1, so an advantage of using a softmax function is that you get a percentage of how confident the network is in this classification. Side note: As DuttaA has commented, cross entropy loss is a better loss ...


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