New answers tagged

1

Phillipe's excellent answer covers the crux of the subject, so I'm just going to state the obvious: the key difference is the medium and timescale. Biological evolution is a function of the natural world, and typically occurs over a long time span, depending on the organisms and how quickly they produce new generations. (We typically think of biological ...


1

Although there are several good answers, I want to add this paragraph from Reinforcement Learning: An Introduction, page 303, for a more psychological view on the difference. The distinction between model-free and model-based reinforcement learning algorithms corresponds to the distinction psychologists make between habitual and goal-directed control ...


0

Philip's answer is good, but I'll add to it. In a GA, a population of individuals (typically represented by bit strings) is evaluated for its fitness on a particular task. Each individual is evaluated separately by a fitness function than can determine its quality. In the Traveling Salesman Problem, the bit string might represent a sequence of numbers, for ...


0

A genetic algorithm is typically a single population designed to optimise to a specific task, say minimising the distance on the travelling salesman problem. Evolutionary game theory algorithms typically model changes between populations that are in competition, generally by using genetic algorithms as above but framed within a broader competitive ...


1

You are right CNN based models can outperform RNN. You can take a look at this paper where they compared different RNN models with TCN (temporal convolutional networks) on different sequence modeling tasks. Even though there are no big differences in terms of results there are some nice properties that CNN based models offers such as: parallelism, stable ...


3

K-fold cross-validation is probably preferred in terms of completeness and generalization: you ensure that the system has seen the complete dataset for training. However, in deep learning this is often not feasible due to time and power constraints. They can both be used, and there is not one better than the other. It really depends on the specific case, the ...


0

Both methods are fine if used properly. As a rule of thumb, when training time is not an issue, use split method if you have more data than you can use in your model and cross-validation if not. I would suggest handling overfitting by some other means.


2

Purely in terms of overfitting, and assuming you train both for equal amounts of time, 70/30 is probably better but performance is not going to be very good. Not training on %30 of data will make both training and test results equally bad (in my opinion). But it won't overfit, that is for sure. Cross validation (you have in mind 90/10, I assume) will take a ...


3

For the first question, RMSE and Euclidean distance have no difference, not that i know of. For the second question, you only need the common loss function for normal tasks. MSE is a common loss function used in linear regression tasks as well as loss function similar in nature like the RMSE. For classification tasks, Cross Entropy Loss is preferred. For ...


-1

Not quit defferent from other software programs or devices, it just has lots of embeded processors for processing things and some of them are not exactly similar as with the other software devices or from the other devices. Most of its processors, they are automaticaly give functions to its system, depending on how it is being program by the programer/s or ...


2

AI has been redefined recently to machine learning. All programming except machine learning (and we'll come back to this) is embodying human knowledge in terms a computer can follow. EG A text editor has user interface rules, user expectations, a contract with the OS that it has to follow. A programmer puts it all together. This applies to text editors, ...


5

This may be a much simpler explanation than you're looking for, but in Machine Learning Zero to Hero, Google engineer Laurence Moroney summarized it in a way that I thought was brilliant. Paraphrasing from a presentation slide: In traditional programming, you input rules and data and the program outputs answers. In machine learning, you input data and ...


0

Spectral Convolution In a spectral graph convolution, we perform an Eigen decomposition of the Laplacian Matrix of the graph. This Eigen decomposition helps us in understanding the underlying structure of the graph with which we can identify clusters/sub-groups of this graph. This is done in the Fourier space. An analogy is PCA where we understand the spread ...


9

Oliver Mason's answer is quite good, but I think it can be expanded upon a bit. I think there are extra factors that could be popularly interpreted as making AI code difficult to read (as compared to other code): AI code actually is more complex than most code that is written. When we work in AI, we often lose sight of this, but most code ever written does ...


16

Code in AI is not in principle different from any other computer code. After all, you encode algorithms in a way that computers can process them. Having said that, there are a few points where your typical "AI Code" might be different: A lot of (especially early) AI code was more research based and exploratory, so certain programming languages were favoured ...


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....


0

There is indeed a close parallel here, but the concepts are distinct. Every perfect information game is fully observable, but not every fully observable game is a game of perfect information. A game of imperfect information is one in which you lack knowledge of any of the following: The state of the game (e.g. current market prices). The rewards you will ...


22

Losing games to computers because of mistakes made under time pressure was probably a thing about 20 years ago, when Kasparov lost to DeepBlue after such a mistake(correction: it was Kramnik with the blunder, not Kasparov (see edit 2)). But after Kramnik's loss in early 2000s, no world champion ever tried to play against a computer (to my knowledge). ...


0

Not exactly, at least traditionally: in Game Theory, "imperfect information" is most often defined as agents having only partial information about the history of agents' actions, as you correctly noted. But also note that this doesn't refer to the general world facts or state. But "partial observability" is typically used in terms of systems, e.g. in Markov ...


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 ...


4

Your reasoning isn't wrong. Deep Neural Networks (DNNs) have a much larger capacity than simpler ML algorithms (excluding NNs) and can easily memorize even a very complex dataset and overfit. DNNs, however, are so effective because they usually are applied on tasks that are harder, so it's not as easy to overfit. For example an image classifier might be ...


4

The following articles Ising models for networks of real neurons (2006) by Gasper Tkacik et al. Deep neural networks for direct, featureless learning through observation: The case of two-dimensional spin models (2018) by Kyle Mills et al. Inverse Ising inference by combining Ornstein-Zernike theory with deep learning (2017) by Soma Turi, Alpha A. Lee et al. ...


Top 50 recent answers are included