Most Popular

1500 questions
6
votes
1 answer

What are the real-life applications of transfer learning?

What are the real-life applications of transfer learning in machine learning? I am particularly interested in industrial applications of the concept.
6
votes
1 answer

Can two admissable heuristics not dominate each other?

I am working on a project for my artificial intelligence class. I was wondering if I have 2 admissible heuristics, A and B, is it possible that A does not dominate B and B does not dominate A? I am wondering this because I had to prove if each…
JRowan
  • 163
  • 5
6
votes
1 answer

How can we conclude that an optimization algorithm is better than another one

When we test a new optimization algorithm, what the process that we need to do?For example, do we need to run the algorithm several times, and pick a best performance,i.e., in terms of accuracy, f1 score .etc, and do the same for an old optimization…
6
votes
2 answers

Can ML be used to curve fit data based on dataset of example fits?

Say I have x,y data connected by a function with some additional parameters (a,b,c): $$ y = f(x ; a, b, c) $$ Now given a set of data points (x and y) I want to determine a,b,c. If I know the model for $f$, this is a simple curve fitting problem.…
argentum2f
  • 181
  • 1
  • 7
6
votes
1 answer

Are there RL techniques to deal with incremental action spaces?

Let's say we have a problem that can be solved by some RL algorithms (DQN, for example, because we have discrete action space). At first, the action space is fixed (the number of actions is $n_1$), and we have already well trained an offline DQN…
6
votes
2 answers

What are the advantages of the Kullback-Leibler over the MSE/RMSE?

I've recently encountered different articles that are recommending to use the KL divergence instead of the MSE/RMSE (as the loss function), when trying to learn a probability distribution, but none of the articles are giving a clear reasoning why…
6
votes
1 answer

How do I know when to use which Monte Carlo method?

I'm a bit confused with extensive number of different Monte Carlo methods such as: Hamiltonian/Hybrid Monte Carlo (HMC), Dynamic Monte Carlo (DMC), Markov chain Monte Carlo (MCMC), Kinetic Monte Carlo (KMC), Dynamic Monte Carlo (DMC) Quasi-Monte…
kenorb
  • 10,525
  • 6
  • 45
  • 95
6
votes
3 answers

Why did a Tesla car mistake a truck with a bright sky?

Do we know why Tesla's autopilot mistaken empty sky with a high-sided lorry which resulted in fatal crash involving a car in self-drive mode? Was it AI fault or something else? Is there any technical explanation behind this why this happened? The…
kenorb
  • 10,525
  • 6
  • 45
  • 95
6
votes
1 answer

How is the gradient of the loss function in DQN derived?

In the original DQN paper, page 1, the loss function of the DQN is $$ L_{i}(\theta_{i}) = \mathbb{E}_{(s,a,r,s') \sim U(D)} [(r+\gamma \max_{a'} Q(s',a',\theta_{i}^{-}) - Q(s,a;\theta_{i}))^2] $$ whose gradient is presented (on page…
6
votes
1 answer

Benchmarks for reinforcement learning in discrete MDPs

To compare the performance of various algorithms for perfect information games, reasonable benchmarks include reversi and m,n,k-games (generalized tic-tac-toe). For imperfect information games, something like simplified poker is a reasonable…
6
votes
3 answers

What are the state-of-the-art approaches for continual learning with neural networks?

There seems to be a lot of literature and research on the problems of stochastic gradient descent and catastrophic forgetting, but I can't find much on solutions to perform continual learning with neural network architectures. By continual learning,…
6
votes
4 answers

Why isn't conditional probability sufficient to describe causality?

I read these comments from Judea Pearl saying we don't have causality, physical equations are symmetric, etc. But the conditional probability is clearly not symmetric and captures directed relationships. How would Pearl respond to someone saying…
6
votes
1 answer

Is there any use of using 3D convolutions for traditional images (like cifar10, imagenet)?

I am curious if there is any advantage of using 3D convolutions on images like CIFAR-10/100 or ImageNet. I know that they are not usually used on this data set, though they could because the channel could be used as the "depth" channel. I know that…
6
votes
1 answer

How to show temporal difference methods converge to MLE?

In chapter 6 of Sutton and Barto (p. 128), they claim temporal difference converges to the maximum likelihood estimate (MLE). How can this be shown formally?
6
votes
1 answer

Video summarization similar to Summe's TextRank

We have the popular TextRank API which given a text, ranks keywords and can apply summarization given a predefined text length. I am wondering if there is a similar tool for video summarization. Maybe a library, a deep model or ML-based tool that…