Greatest Hits

64 votes
6 answers
66k views

What's the difference between model-free and model-based reinforcement learning?

What's the difference between model-free and model-based reinforcement learning? It seems to me that any model-free learner, learning through trial and error, could be reframed as model-based. In ...
user avatar
173 votes
12 answers
49k views

Could a paradox kill an AI?

In Portal 2 we see that AI's can be "killed" by thinking about a paradox. I assume this works by forcing the AI into an infinite loop which would essentially "freeze" the computer's consciousness. ...
user avatar
  • 1,849
84 votes
3 answers
76k views

What is self-supervised learning in machine learning?

What is self-supervised learning in machine learning? How is it different from supervised learning?
user avatar
  • 33k
7 votes
4 answers
68k views

Is "AIAngel" (Patreon) a fake?

These guys here: https://www.patreon.com/AiAngel are saying that they've created a AI who can chat and stream. As the so-called administrator "Rogue" said: this chat/streamer bot are no fake. Also, ...
user avatar
  • 181
37 votes
5 answers
70k views

What is the difference between a convolutional neural network and a regular neural network?

I've seen these terms thrown around this site a lot, specifically in the tags convolutional-neural-networks and neural-networks. I know that a neural network is a system based loosely on the human ...
user avatar
  • 1,688
23 votes
4 answers
61k views

Why does C++ seem less widely used than Python in AI?

I just want to know why do machine learning engineers and AI programmers use languages like Python to perform AI tasks and not C++, even though C++ is technically a more powerful language than Python.
user avatar
43 votes
4 answers
43k views

Why does the transformer do better than RNN and LSTM in long-range context dependencies?

I am reading the article How Transformers Work where the author writes Another problem with RNNs, and LSTMs, is that it’s hard to parallelize the work for processing sentences, since you have to ...
user avatar
  • 1,213
52 votes
4 answers
92k views

How to select number of hidden layers and number of memory cells in an LSTM?

I am trying to find some existing research on how to select the number of hidden layers and the size of these of an LSTM-based RNN. Is there an article where this problem is being investigated, i.e., ...
user avatar
59 votes
10 answers
47k views

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

My understanding is that the convolutional layer of a convolutional neural network has four dimensions: ...
user avatar
8 votes
3 answers
44k views

What are the differences between A* and greedy best-first search?

What are the differences between the A* algorithm and the greedy best-first search algorithm? Which one should I use? Which algorithm is the better one, and why?
user avatar
7 votes
1 answer
30k views

What are some examples of intelligent agents for each intelligent agent class?

There are several classes of intelligent agents, such as: simple reflex agents model-based reflex agents goal-based agents utility-based agents learning agents Each of these agents behaves slightly ...
user avatar
82 votes
3 answers
59k views

How can neural networks deal with varying input sizes?

As far as I can tell, neural networks have a fixed number of neurons in the input layer. If neural networks are used in a context like NLP, sentences or blocks of text of varying sizes are fed to a ...
user avatar
  • 961
19 votes
1 answer
29k views

What is the difference between tree search and graph search?

I have read various answers to this question at different places, but I am still missing something. What I have understood is that a graph search holds a closed list, with all expanded nodes, so ...
user avatar
  • 413
61 votes
10 answers
42k views

Why is Python such a popular language in the AI field?

First of all, I'm a beginner studying AI and this is not an opinion-oriented question or one to compare programming languages. I'm not implying that Python is the best language. But the fact is that ...
user avatar
12 votes
2 answers
39k views

How can these 7 AI problem characteristics help me decide on an approach to a problem?

If this list1 can be used to classify problems in AI ... Decomposable to smaller or easier problems Solution steps can be ignored or undone Predictable problem universe Good solutions are ...
user avatar
  • 121
25 votes
2 answers
25k views

What are "bottlenecks" in neural networks?

What are "bottlenecks" in the context of neural networks? This term is mentioned, for example, in this TensorFlow article, which also uses the term "bottleneck values". How does ...
user avatar
23 votes
3 answers
30k views

Can BERT be used for sentence generating tasks?

I am a new learner in NLP. I am interested in the sentence generating task. As far as I am concerned, one state-of-the-art method is the CharRNN, which uses RNN to generate a sequence of words. ...
user avatar
  • 333
35 votes
4 answers
38k views

What is the time complexity for training a neural network using back-propagation?

Suppose that a NN contains $n$ hidden layers, $m$ training examples, $x$ features, and $n_i$ nodes in each layer. What is the time complexity to train this NN using back-propagation? I have a basic ...
user avatar
19 votes
1 answer
16k views

What is the credit assignment problem?

In reinforcement learning (RL), the credit assignment problem (CAP) seems to be an important problem. What is the CAP? Why is it relevant to RL?
user avatar
  • 33k
24 votes
3 answers
41k views

How do I handle large images when training a CNN?

Suppose that I have 10K images of sizes $2400 \times 2400$ to train a CNN. How do I handle such large image sizes without downsampling? Here are a few more specific questions. Are there any ...
user avatar
18 votes
3 answers
43k views

How do I choose the optimal batch size?

Batch size is a term used in machine learning and refers to the number of training examples utilised in one iteration. The batch size can be one of three options: batch mode: where the batch size is ...
user avatar
27 votes
5 answers
34k views

How can I deal with images of variable dimensions when doing image segmentation?

I'm facing the problem of having images of different dimensions as inputs in a segmentation task. Note that the images do not even have the same aspect ratio. One common approach that I found in ...
user avatar
  • 537
26 votes
4 answers
33k views

Can a neural network be used to predict the next pseudo random number?

Is it possible to feed a neural network the output from a random number generator and expect it learn the hashing (or generator) function, so that it can predict what will be the next generated pseudo-...
user avatar
  • 371
45 votes
19 answers
15k views

Can digital computers understand infinity?

As a human being, we can think infinity. In principle, if we have enough resources (time etc.), we can count infinitely many things (including abstract, like numbers, or real). For example, at least, ...
user avatar
  • 658
8 votes
1 answer
11k views

What is the difference between an agent function and an agent program?

In section 2.4 (p. 46) of the book Artificial Intelligence: A modern approach (3rd edition), Russell and Norvig write The job of AI is to design an agent program that implements the agent function — ...
user avatar
13 votes
8 answers
19k views

How to classify data which is spiral in shape?

I have been messing around in tensorflow playground. One of the input data sets is a spiral. No matter what input parameters I choose, no matter how wide and deep the neural network I make, I cannot ...
user avatar
12 votes
1 answer
14k views

What is a fully convolution network?

I was surveying some literature related to Fully Convolutional Networks and came across the following phrase, A fully convolutional network is achieved by replacing the parameter-rich fully ...
user avatar
11 votes
13 answers
14k views

Is AI living or non-living?

I'm a bit confused about the definition of life. Can AI systems be called 'living'? Because they can do most of the things that we can. They can even communicate with one another. They are not ...
user avatar
  • 379
34 votes
5 answers
21k views

What is the purpose of an activation function in neural networks?

It is said that activation functions in neural networks help introduce non-linearity. What does this mean? What does non-linearity mean in this context? How does the introduction of this non-...
user avatar
40 votes
6 answers
21k views

How do capsule neural networks work?

Geoffrey Hinton has been researching something he calls "capsules theory" in neural networks. What is it? How do capsule neural networks work?
user avatar
  • 1,979
44 votes
3 answers
23k views

What is the difference between strong-AI and weak-AI?

I've heard the terms strong-AI and weak-AI used. Are these well defined terms or subjective ones? How are they generally defined?
user avatar
  • 2,293
10 votes
2 answers
17k views

What are the limitations of the hill climbing algorithm and how to overcome them?

What are the limitations of the hill climbing algorithm? How can we overcome these limitations?
user avatar
  • 536
7 votes
6 answers
12k views

What is the difference between artificial intelligence and robots?

What is the difference between artificial intelligence and robots?
user avatar
  • 992
12 votes
2 answers
14k views

What are bottleneck features?

In the blog post Building powerful image classification models using very little data, bottleneck features are mentioned. What are the bottleneck features? Do they change with the architecture that is ...
user avatar
21 votes
5 answers
12k views

What is non-Euclidean data?

What is non-Euclidean data? Here are some sub-questions Where does this type of data arise? I have come across this term in the context of geometric deep learning and graph neural networks. ...
user avatar
  • 33k
37 votes
2 answers
17k views

What is the relation between Q-learning and policy gradients methods?

As far as I understand, Q-learning and policy gradients (PG) are the two major approaches used to solve RL problems. While Q-learning aims to predict the reward of a certain action taken in a certain ...
user avatar
  • 495
97 votes
14 answers
6k views

How could self-driving cars make ethical decisions about who to kill?

Obviously, self-driving cars aren't perfect, so imagine that the Google car (as an example) got into a difficult situation. Here are a few examples of unfortunate situations caused by a set of events: ...
user avatar
  • 10k
55 votes
4 answers
15k views

Are neural networks prone to catastrophic forgetting?

Imagine you show a neural network a picture of a lion 100 times and label it with "dangerous", so it learns that lions are dangerous. Now imagine that previously you have shown it millions ...
user avatar
  • 2,014
9 votes
1 answer
14k views

What is the fringe in the context of search algorithms?

What is the fringe in the context of search algorithms?
user avatar
34 votes
4 answers
18k views

Could a neural network detect primes?

I am not looking for an efficient way to find primes (which of course is a solved problem). This is more of a "what if" question. So, in theory, could you train a neural network to predict ...
user avatar
  • 453
16 votes
2 answers
12k views

What is the difference between First-Visit Monte-Carlo and Every-Visit Monte-Carlo Policy Evaluation?

I came across these 2 algorithms, but I cannot understand the difference between these 2, both in terms of implementation as well as intuitionally. So, what difference does the second point in both ...
user avatar
12 votes
1 answer
19k views

Why is A* optimal if the heuristic function is admissible?

A heuristic is admissible if it never overestimates the true cost to reach the goal node from $n$. If a heuristic is consistent, then the heuristic value of $n$ is never greater than the cost of its ...
user avatar
  • 293
34 votes
3 answers
27k views

Why is Lisp such a good language for AI?

I've heard before from computer scientists and from researchers in the area of AI that that Lisp is a good language for research and development in artificial intelligence. Does this still apply, ...
user avatar
54 votes
13 answers
10k views

How could artificial intelligence harm us?

We often hear that artificial intelligence may harm or even kill humans, so it might prove dangerous. How could artificial intelligence harm us?
user avatar
  • 651
11 votes
3 answers
9k views

How is Bayes' Theorem used in artificial intelligence and machine learning?

How is Bayes' Theorem used in artificial intelligence and machine learning? As a high school student, I will be writing an essay about it, and I want to be able to explain Bayes' Theorem, its general ...
user avatar
91 votes
10 answers
15k views

What is the difference between artificial intelligence and machine learning?

These two terms seem to be related, especially in their application in computer science and software engineering. Is one a subset of another? Is one a tool used to build a system for the other? What ...
user avatar
  • 1,205
22 votes
1 answer
10k views

What is the Bellman operator in reinforcement learning?

In mathematics, the word operator can refer to several distinct but related concepts. An operator can be defined as a function between two vector spaces, it can be defined as a function where the ...
user avatar
  • 33k
68 votes
9 answers
10k views

Why do we need explainable AI?

If the original purpose for developing AI was to help humans in some tasks and that purpose still holds, why should we care about its explainability? For example, in deep learning, as long as the ...
user avatar
  • 2,511
27 votes
7 answers
15k views

How can an AI train itself if no one is telling it if its answer is correct or wrong?

I am a programmer but not in the field of AI. A question constantly confuses me is that how can an AI be trained if we human beings are not telling it its calculation is correct? For example, news ...
user avatar
33 votes
5 answers
22k views

Is it possible to train the neural network to solve math equations?

I'm aware that neural networks are probably not designed to do that, however asking hypothetically, is it possible to train the deep neural network (or similar) to solve math equations? So given the ...
user avatar
  • 10k