96 votes
Accepted

What is self-supervised learning in machine learning?

Introduction The term self-supervised learning (SSL) has been used (sometimes differently) in different contexts and fields, such as representation learning [1], neural networks, robotics [2], natural ...
nbro's user avatar
  • 40.2k
19 votes

What is self-supervised learning in machine learning?

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 ...
David's user avatar
  • 511
14 votes
Accepted

What are the different approaches used in Machine Learning?

Things in italics should give you enough googleable terms to start a deeper dive :P. There are 3 main branches of statistical ML. Supervised Learning This approach is taken when a problem can be ...
Jaden Travnik's user avatar
14 votes
Accepted

Can supervised learning be recast as reinforcement learning problem?

Any supervised learning (SL) problem can be cast as an equivalent reinforcement learning (RL) one. Suppose you have the training dataset $\mathcal{D} = \{ (x_i, y_i \}_{i=1}^N$, where $x_i$ is an ...
nbro's user avatar
  • 40.2k
13 votes
Accepted

What is "planning" in the context of reinforcement learning, and how is it different from RL and SL?

The concept of "planning" is not just related to RL. In general (as the name suggests), planning consists in creating a "plan" which you will use to reach a "goal". The ...
nbro's user avatar
  • 40.2k
10 votes

What is the relation between semi-supervised and self-supervised visual representation learning?

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 ...
Amit Chaudhary's user avatar
8 votes

What is the relation between semi-supervised and self-supervised visual representation learning?

Semi-supervised learning Semi-supervised learning is the collection of machine learning techniques where there are two datasets: a labelled one and an unlabelled one. There are two main problems that ...
nbro's user avatar
  • 40.2k
7 votes
Accepted

Does AlphaZero use Q-Learning?

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 ...
Dennis Soemers's user avatar
  • 10.2k
7 votes

What is self-supervised learning in machine learning?

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 ...
ssegvic's user avatar
  • 499
6 votes

How to generate labels for self-supervised training?

How can I generate the target label from the other data in the dataset? If you are asking how you can create the learning signal in SSL, when given an unlabelled dataset, for learning representations ...
nbro's user avatar
  • 40.2k
5 votes
Accepted

What is the difference between imitation learning and classification done by experts?

Imitation learning is supervised learning applied to the RL setting. In any general RL algorithm (such as Q-learning), the learning is done on the basis of the reward function. However, consider a ...
Sabyasachi Ghosh's user avatar
5 votes

Why are neural networks always trained "by themselves"?

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 ...
Free's user avatar
  • 61
5 votes

What is the relation between semi-supervised and self-supervised visual representation learning?

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 ...
Shamane Siriwardhana's user avatar
5 votes
Accepted

How can supervised learning be viewed as a conditional probability of the labels given the inputs?

This formulation/interpretation can indeed be confusing (or even misleading), as the output of a neural network is usually deterministic (i.e. given the same input $x$, the output is always the same, ...
nbro's user avatar
  • 40.2k
5 votes
Accepted

What is the meaning of "exploration" in reinforcement and supervised learning?

In reinforcement learning, exploration has a specific meaning, which is in contrast with the meaning of exploitation, hence the so-called exploration-exploitation dilemma (or trade-off). You explore ...
nbro's user avatar
  • 40.2k
4 votes
Accepted

How Does AlphaGo Zero Implement Reinforcement Learning?

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 ...
nbro's user avatar
  • 40.2k
4 votes

How could decision tree learning algorithms cope with imbalanced classes?

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 ...
John Doucette's user avatar
3 votes

How is regression machine learning?

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 ...
mshlis's user avatar
  • 2,359
3 votes
Accepted

Are the training loss and validation loss plotted per sample or per batch?

You want to compute the mean loss over all batches. What you need to do is to divide the sum of batch losses with the number of batches! In your case: You have a training set of $21700$ samples and ...
Djib2011's user avatar
  • 3,183
3 votes
Accepted

What is the difference between reinforcement learning and AutoML?

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 ...
nbro's user avatar
  • 40.2k
3 votes
Accepted

Is it possible to guide a reinforcement learning algorithm?

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 ...
nbro's user avatar
  • 40.2k
3 votes
Accepted

How can reinforcement learning be unsupervised learning if it uses deep learning?

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 ...
nbro's user avatar
  • 40.2k
3 votes
Accepted

How is the reward in reinforcement learning different from the label in supervised learning problems?

Reward in reinforcement learning (RL) is entirely different from a supervised learning (SL) label, but can be related to it indirectly. In a RL control setting, you can imagine that you had a data ...
Neil Slater's user avatar
  • 31.7k
3 votes
Accepted

How can we teach a neural net to make arbitrary data associations?

In a nutshell : Memorizing is not Learning So, first let's just remind the classical use of a neural net, in Supervised Learning : You have a set of $(x_{train}, y_{train}) \in X \times Y$ pairs, and ...
16Aghnar's user avatar
  • 601
3 votes
Accepted

Can we use ML to do anything else other than predicting (in the case of mathematical problems)?

There are quite a few examples of papers where they try and 'teach' neural networks to 'learn' how to solve math problems. Most of the time, sadly, it comes down to training on a large dataset after ...
Robin van Hoorn's user avatar
3 votes

Is validation data needed with generated training data?

TL;DR: You always need held-out (unseen) data to know if a model 'generalises' to new data and to evaluate it (to compare models, hyper-parameters, assess performance over the training phase etc.) If ...
Carl's user avatar
  • 141
2 votes
Accepted

Does neuroevolution require a labelled dataset?

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 ...
Thomas Wagenaar's user avatar
2 votes

Can autoencoders be used for supervised learning?

One such paper I know of and which I implemented is Semi-Supervised Learning using Ladder Networks . I quote here their description of the model: Our approach follows Valpola (2015), who proposed a ...
AlexGuevara's user avatar
2 votes

Are these steps to get a final linear regression model correct?

In general these steps are correct, but are few clarifications would be good. For supervised learning, you can: pick model to use split data into training and test set train model, or determine ...
sma's user avatar
  • 823
2 votes

What is the difference between imitation learning and classification done by experts?

I also had the same question, but after looking at this two links: this article and this lecture I think we can say that behavioral cloning (which is the simplest way for doing imitation learning) is ...
Abdalwhab Bakheet's user avatar

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