Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Most Popular

more tags
1500 questions
9
votes
3 answers

Why is cross-over a part of genetic algorithms?

Genetic Algorithms has come to my attention recently when trying to correct/improve computer opponents for turn-based strategy computer games. I implemented a simple Genetic Algorithm that didn't use any cross-over, just some random mutation. It…
Mithical
  • 2,905
  • 5
  • 27
  • 39
9
votes
2 answers

What kind of education is required for researchers in AI?

Suppose my goal is to collaborate and create an advanced AI, for instance, one that resembles a human being and the project would be on the frontier of AI research. What kind of skills would I need? I am talking about specific things, like what…
user289661
  • 419
  • 3
  • 11
9
votes
1 answer

What kind of body (if any) does intelligence require?

In the mid 1980s, Rodney Brooks famously created the foundations of "the new AI". The central claim was that the symbolist approach of 'Good Old Fashioned AI' (GOFAI) had failed by attempting to 'cream cognition off the top', and that embodied…
NietzscheanAI
  • 7,256
  • 23
  • 37
9
votes
3 answers

Is a GPU always faster than a CPU for training neural networks?

Currently, I am working on a few projects that use feedforward neural networks for regression and classification of simple tabular data. I have noticed that training a neural network using TensorFlow-GPU is often slower than training the same…
GKozinski
  • 1,260
  • 9
  • 19
9
votes
4 answers

What could an oscillating training loss curve represent?

I tried to create a simple model that receives an $80 \times 130$ pixel image. I only had 35 images and 10 test images. I trained this model for a binary classification task. The architecture of the model is described below. conv2d_1 (Conv2D) …
Krishnakumar
  • 91
  • 1
  • 1
  • 2
9
votes
3 answers

Is it beneficial to represent a neural net as a matrix?

A neural network is a directed weighted graph. These can be represented by a (sparse) matrix. Doing so can expose some elegant properties of the network. Is this technique beneficial for examining neural networks?
ratchet freak
  • 191
  • 1
  • 2
9
votes
3 answers

How is it possible that the MSE used to train neural networks with gradient descent has multiple local minima?

We often train neural networks by optimizing the mean squared error (MSE), which is an equation of a parabola $y=x^2$, with gradient descent. We also say that weight adjustment in a neural network by the gradient descent algorithm can hit a local…
isnvi23h4
  • 213
  • 2
  • 10
9
votes
1 answer

Are there reinforcement learning algorithms that scale to large problems?

Given a large problem, value iteration and other table based approaches seem to require too many iterations before they start to converge. Are there other reinforcement learning approaches that better scale to large problems and minimize the amount…
Jan
  • 351
  • 3
  • 13
9
votes
2 answers

What is the difference between search and learning?

I came across an article, The Bitter Truth, via the Two Minute Papers YouTube Channel. Rich Sutton says... One thing that should be learned from the bitter lesson is the great power of general purpose methods, of methods that continue to scale with…
nvi
  • 93
  • 4
9
votes
1 answer

Is back-propagation applied for each data point or for a batch of data points?

I am new to deep learning and trying to understand the concept of back-propagation. I have a doubt about when the back-propagation is applied. Assume that I have a training data set of 1000 images for handwritten letters, Is back-propagation…
Maanu
  • 235
  • 1
  • 2
  • 6
9
votes
1 answer

What causes a model to require a low learning rate?

I've pondered this for a while without developing an intuition for the math behind the cause of this. So what causes a model to need a low learning rate?
JohnAllen
  • 217
  • 1
  • 6
9
votes
1 answer

How do I use GPT-2 to summarise text?

In section 3.6 of the OpenAI GPT-2 paper it mentions summarising text based relates to this, but the method is described in very high-level terms: To induce summarization behavior we add the text TL;DR: after the article and generate 100 tokens…
Tom Hale
  • 364
  • 3
  • 11
9
votes
2 answers

What are the main advantages of using declarative programming languages for building AI?

What specific advantages of declarative languages make them more applicable to AI than imperative languages? What can declarative languages do easily that other languages styles find difficult for this kind of problem?
intcreator
  • 1,335
  • 2
  • 10
  • 15
9
votes
1 answer

What is the difference between an episode, a trajectory and a rollout?

I often see the terms episode, trajectory, and rollout to refer to basically the same thing, a list of (state, action, rewards). Are there any concrete differences between the terms or can they be used interchangeably? In the following paragraphs,…
Paula Vega
  • 428
  • 4
  • 8
8
votes
3 answers

Is it possible to use AI to reverse engineer software?

I was thinking of something of the sort: Build a program (call this one fake user) that generates lots and lots and lots of data based on the usage of another program (call this one target) using stimuli and response. For example, if the target is…
IpsumPanEst
  • 81
  • 1
  • 2
1 2 3
…
99 100