16 votes

How do neural networks play chess?

Minimax and related algorithms are used to play chess. That is how chess programs have worked for many years (with some additions such as standard opening playbooks). They do not need to process the ...
user avatar
  • 23.8k
10 votes

How do neural networks play chess?

This is a good question. your understanding in general is correct. Indeed, data can be used to construct a proper evaluation of a move/board position and recommended moves based on its history (at ...
user avatar
  • 749
4 votes

Is there any way to train a neural network without using gradients?

Yes. A prominent class of "gradient-free" algorithms in ML world is known as Evolution Strategies (ES). Evolutionary Algorithms, although existed for a long time, only a few have shown to ...
user avatar
  • 238
4 votes

How should I read a deep learning paper?

Adding something to nbro answer, from my personal experience there are also some hints that can quickly tell you if you're dealing with a good machine learning paper, i.e. worth to read in its ...
user avatar
4 votes
Accepted

What are knowledge graph embeddings?

Knowledge graph embeddings (KGE) are embeddings created in the context of a knowledge graph (KG), which can be viewed as a visual/graphical representation of a knowledge base, where nodes are entities ...
user avatar
  • 33.8k
4 votes
Accepted

Does the term "data augmentation" imply increasing the training dataset?

I'm not familiar with any "authoritative" single definition somewhere, or not sure who used the term first, but I would personally indeed agree with the reviewer you mention. In fact I've ...
user avatar
  • 9,369
4 votes
Accepted

Is there a standardized method to train a reinforcement learning NN by demonstration?

Yes, this is known as imitation learning, which can be divided into inverse RL (i.e. learn a reward function from demonstrations, then apply RL), and behaviour cloning (supervised learning applied to ...
user avatar
  • 33.8k
3 votes
Accepted

Does regularization just mean using an augmented loss function?

Regularization is not limited to methods like L1/L2 regularization which are specific versions of what you showed. Regularization is any technique that would prevent network from overfitting and help ...
user avatar
2 votes

Where can I find the original paper that introduced RNNs?

According to this meta paper, "vanilla" RNN of today are based on Elman's work on networks with dynamic memory: Finding structure in time
user avatar
2 votes

Has machine learning been combined with logical reasoning (for example, PROLOG)?

Another example where machine learning has been combined with symbolic AI is in the context of knowledge graphs (which can be viewed as a graphical/visual representation of a knowledge base), where ...
user avatar
  • 33.8k
2 votes

What is the state of the art in melody generation?

you do not need ai for that, just a little bit of math / statistics: audio: https://m.soundcloud.com/user-919775337/sets/algorithmic-reinterpretation method: https://stats.stackexchange.com/questions/...
user avatar
2 votes

Is there any other (possibly less popular) approach to create AI apart from statistical methods?

Yes, there is symbolic AI. This was the 'original' approach to AI, at a time when there was very little data and/or processing power available. The focus was on logic and calculus, not on machine ...
user avatar
  • 5,062
2 votes

How should I read a deep learning paper?

I have some experience reading research papers. However, in my view, there is no single answer to this question (apart from this answer I am giving you, i.e. "it depends"). The answer to ...
user avatar
  • 33.8k
2 votes

Which introductory courses (preferably video lectures) could I use to learn ML for applying ML to black hole simulations?

Cornell University offers lecture notes and videos of over thirty machine learning related courses in this link. CS4780 Introduction to Machine Learning in particular is a great resource (lecture ...
user avatar
  • 522
2 votes

Is there a mathematical formalism to deal with a missing reward signal?

Your setting (of randomly dropping out reward signals) impacts expected future reward by multiply everything by a common factor $(1-\epsilon)$. As reinforcement learning (RL) control is based on ...
user avatar
  • 23.8k
2 votes
Accepted

How to train an ML model to convert the given lyrics into a song by a particular singer?

OpenAI used a modified version of VQ-VAE-2 combined with sparse transformers to do something similar to what you want to do. Their approach, called Jukebox, is able to produce music by conditioning on ...
user avatar
  • 33.8k
2 votes

Are there any works that deal with 2D pose estimation in videos?

Update: I misread the question; It seems like OP is more interested in pose tracking. So, I'll have to point OP to papers on that, like this one. Using multiple frames becomes especially important ...
user avatar
  • 406
2 votes

How to model a multi-agent reinforcement learning problem where actions of different agents can take different durations?

You could take a look into options, (discrete-time) semi-MDPs, and multi-agent RL. An option is a generalisation of an action. Mathematically, it's defined as a tuple $\langle\mathcal{I}, \pi, \beta\...
user avatar
  • 33.8k
2 votes

How to construct a reward function for a "wait and see" problem

In general, the term of art for this problem is "early classification." Early classification of time series has been extensively studied for minimizing class prediction delay in time-...
user avatar
  • 236
1 vote
Accepted

Would AlphaZero work just with a value network?

I'm not aware of anyone running a setup of everything that AlphaZero does, minus the Policy Network, and reporting on how well it worked, so I don't think I can provide a definitive 100% certain ...
user avatar
  • 9,369
1 vote
Accepted

Is there an entry level textbook on Bayesian Inference that is a nice blend of theory and applications?

Using as a best reference accordingly my own google research, find the best post about best introductory Bayesian statistics book and summarize the answers. I find this post in stats.stackexchange ...
user avatar
1 vote

Does regularization just mean using an augmented loss function?

Also, keep in mind that not just any augmentation of the loss function is a regularization. For example, you can add terms to a loss function that enforce constraints on the solution but do not ...
user avatar
  • 121
1 vote

Is there any other (possibly less popular) approach to create AI apart from statistical methods?

What you're looking for are Expert systems and Knowledge Based Systems. Really similar to each other, they encompass all systems built upon experts knowledge, from which analytic rules are derived in ...
user avatar
1 vote
Accepted

Is there any paper that shows that multi-channel neural networks are universal approximators?

Yes, there is such a statement, valid even in a bit more general setting. Any function, equivariant to a certain symmetry, can be approximated arbitrarily well, provided that the number of parameters ...
user avatar
1 vote
Accepted

CNN Architectures for local features vs global context

Well, in regards to properties of CNNs in regards to local versus global features, you should familiarize yourself with the concepts of invariance and equivariance. At some point you should also learn ...
user avatar
  • 406
1 vote
Accepted

Is there a benchmark for multi-objective evolutionary algorithms?

The DEAP library (a Python library for EAs) contains some benchmarks. In particular, you may want to look at the following functions Function(s) Reference/paper ...
user avatar
  • 33.8k
1 vote
Accepted

What is the name of the method for the smart extend of image surroundings?

In computer vision, the problem of filling missing parts of an image is called image inpainting; the subtask of filling the surroundings is called image outpainting in [1], which is your problem. The ...
user avatar
  • 33.8k
1 vote

Where can I read about upsampling methods in detail?

Tricky question. In my experience is better to just look for math resources on classic upsampling method, since deep learning papers and books tend to give them for granted, or not something related ...
user avatar

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