Most Popular

1500 questions
7
votes
2 answers

What are the major differences between multi-armed bandits and the other well-known algorithms (DQN, A3C, PPO, etc)?

I have studied in the past different algorithms, i.e. DQN, DDQN, REINFORCE, A3C, PPO, TRPO, so on. I am doing an internship this summer where I have to use a multi-armed bandit (MAB). I am a bit confused between MAB and the other above…
7
votes
2 answers

Origins of the name of convolutional neural networks

Convolutional neural networks (CNNs) contain convolutional layers. In modern deep learning libraries such as Tensorflow and PyTorch, convolutional layers are implemented by using the cross-correlation operator instead of the convolution operator.…
7
votes
2 answers

What does "semantic gap" mean?

I was reading DT-LET: Deep transfer learning by exploring where to transfer, and it contains the following: It should be noted direct use of labeled source domain data on a new scene of target domain would result in poor performance due to the…
7
votes
1 answer

What will happen when you place a fake speedsign on a highway?

I was wondering what will happen when somebody places a fake speedsign, of 10 miles per hour on a high way. Will a autonomous car slow down? Is this a current issue of autonomous cars?
7
votes
5 answers

Why is the Turing test so popular?

I know there are different AI tests but I'm wondering why other tests are little-known. Is the Turing test hyped? Are there any scientific reasons to prefer one test to the other? Why is the Turing test so popular?
user4801
7
votes
1 answer

How to deal with losses on different scales in multi-task learning?

Say I'm training a model for multiple tasks by trying to minimize sum of losses $L_1 + L_2$ via gradient descent. If these losses are on a different scale, the one whose range is greater will dominate the optimization. I'm currently trying to fix…
7
votes
1 answer

What should we do when the selection step selects a terminal state?

In Monte Carlo tree search, what should we do when the selection step selects a terminal state (i.e. a won or lost state), which is, by definition, a leaf node? Expansion and simulation is not in order, as it's game over, but does the tree…
degski
  • 173
  • 6
7
votes
2 answers

How is this Pytorch expression equivalent to the KL divergence?

I found the following PyTorch code (from this link) -0.5 * torch.sum(1 + sigma - mu.pow(2) - sigma.exp()) where mu is the mean parameter that comes out of the model and sigma is the sigma parameter out of the encoder. This expression is apparently…
7
votes
4 answers

Which artificial neural network can mimic biological neurons the most?

On the Wikipedia page we can read the basic structure of an artificial neuron (a model of biological neurons) which consist: Dendrites - acts as the input vector, Soma - acts as the summation function, Axon - gets its signal from the summation…
kenorb
  • 10,525
  • 6
  • 45
  • 95
7
votes
1 answer

Which rules should I define for the predicate "not_to_far" of the exercise 1.1 of the book "Simply Logical: Intelligent Reasoning by Example"?

I've just started reading a book about AI. The book is Simply Logical: Intelligent Reasoning by Example. There is a very basic exercise (on page 19 of the pdf, page 5 of the book), but I can't figure it out. The exercise is Exercise 1.1. Two…
ihavenokia
  • 173
  • 2
  • 6
7
votes
2 answers

Is there a proof to explain why XOR cannot be linearly separable?

Can someone explain to me with a proof or example why you can't linearly separate XOR (and therefore need a neural network, the context I'm looking at it in)? I understand why it's not linearly separable if you draw it graphically (e.g. here), but I…
Slowat_Kela
  • 307
  • 1
  • 3
  • 9
7
votes
1 answer

Could an AI be killed in an infinite loop?

Currently, we use control flow statements (such as loops) to program the artificially intelligent systems. Could an AI be killed in an infinite loop (created by itself, for example, while manipulating its source code)? The question isn't baseless,…
Parth Raghav
  • 345
  • 1
  • 8
7
votes
1 answer

What difference does it make whether Actor and Critic share the same network or not?

I'm learning about Actor-Critic reinforcement learning algorithms. One source I encountered mentioned that Actor and Critic can either share one network (but use different output layers) or they can use two completely separate networks. In this…
7
votes
2 answers

Are convolutional neural networks inspired by the human brain?

The Deep Learning book by Goodfellow et al. states Convolutional networks stand out as an example of neuroscientific principles influencing deep learning. Are convolutional neural networks (CNNs) really inspired by the human brain? If so, how? In…
7
votes
1 answer

What is the difference between Stochastic Hill Climbing and Simulated Annealing?

I am reading about local search: hill climbing, and its types, and simulated annealing One of the hill climbing versions is "stochastic hill climbing", which has the following definition: Stochastic hill climbing does not examine for all its…