40 votes

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

TLDR: The convolutional-neural-network is a subclass of neural-networks which have at least one convolution layer. They are great for capturing local information (e.g. neighbor pixels in an image or ...
user avatar
36 votes
Accepted

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

The terms strong and weak don't actually refer to processing, or optimization power, or any interpretation leading to "strong AI" being stronger than "weak AI". It holds conveniently in practice, but ...
user avatar
  • 536
30 votes
Accepted

What is the credit assignment problem?

In reinforcement learning (RL), an agent interacts with an environment in time steps. On each time step, the agent takes an action in a certain state and the environment emits a percept or perception, ...
user avatar
  • 33.8k
27 votes
Accepted

What are the minimum requirements to call something AI?

It's true that the term has become a buzzword, and is now widely used to a point of confusion - however if you look at the definition provided by Stuart Russell and Peter Norvig, they write it as ...
user avatar
  • 666
25 votes
Accepted

What is the concept of the technological singularity?

The technological singularity is a theoretical point in time at which a self-improving artificial general intelligence becomes able to understand and manipulate concepts outside of the human brain's ...
user avatar
  • 758
25 votes
Accepted

What is the idea called involving an AI that will eventually rule humanity?

If I'm not mistaken you're looking for Roko's Basilisk, in which an otherwise benevolent future AI system tortures simulations of those who did not work to bring the system into existence
user avatar
  • 426
22 votes
Accepted

Are search engines considered AI?

I believe it would be more accurate to say that (some) search engines use AI. Broadly saying "search engines are AI" is not really correct. At the core, most search engines are nothing more than an ...
user avatar
  • 3,677
22 votes
Accepted

Why can't OCR be perceived as a good example of AI?

Whenever a problem becomes solvable by a computer, people start arguing that it does not require intelligence. John McCarthy is often quoted: "As soon as it works, no one calls it AI anymore" (...
user avatar
  • 1,174
19 votes

What is geometric deep learning?

To complete the first answer that is rather graph oriented, I will write a little about deep learning on manifolds, which is quite general in terms of GDL thanks to the nature of manifolds. Note ...
user avatar
  • 301
18 votes

What is the difference between tree search and graph search?

There is always a lot of confusion about this concept, because the naming is misleading, given that both tree and graph searches produce a tree (from which you can derive a path) while exploring the ...
17 votes

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

Convolutional Neural Networks (CNNs) are neural networks with architectural constraints to reduce computational complexity and ensure translational invariance (the network interprets input patterns ...
user avatar
15 votes
Accepted

What is "backprop"?

"Backprop" is the same as "backpropagation": it's just a shorter way to say it. It is sometimes abbreviated as "BP".
user avatar
14 votes

Why can't OCR be perceived as a good example of AI?

Although OCR is now a mainstream technology, it remains true that none our methods genuinely have the recognition facilities of a 5 year old (claimed success with CAPTCHAs notwithstanding). We don't ...
user avatar
14 votes
Accepted

Is AlphaZero an example of an AGI?

Good question! AlphaZero, though a major milestone, is most definitely not an AGI :) AlphaGo, though strong at the game of Go, is narrowly strong ("strong-narrow AI"), defined as strength in a ...
user avatar
  • 6,067
12 votes
Accepted

What is a deep neural network?

A deep neural network (DNN) is nothing but a neural network which has multiple layers, where multiple can be subjective. IMHO, any network which has 6 or 7 or more layers is considered deep. So, the ...
user avatar
  • 1,351
11 votes

What is the definition of "soft label" and "hard label"?

According to Galstyan and Cohen (2007), a hard label is a label assigned to a member of a class where membership is binary: either the element in question is a member of the class (has the label), or ...
user avatar
  • 5,062
11 votes
Accepted

What is non-Euclidean data?

I presume this question was prompted by the paper Geometric deep learning: going beyond Euclidean data (2017). If we look at its abstract: Many scientific fields study data with an underlying ...
user avatar
11 votes

What is a recurrent neural network?

A recurrent neural network (RNN) is an artificial neural network that contains backward or self-connections, as opposed to just having forward connections, like in a feed-forward neural network (FFNN)....
user avatar
  • 33.8k
10 votes

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? It's clearly written in the link you gave ...
user avatar
10 votes

What is the idea called involving an AI that will eventually rule humanity?

I believe the term you are looking for is "(technological) singularity". https://en.wikipedia.org/wiki/Technological_singularity
user avatar
  • 202
9 votes
Accepted

Does the recent advent of a Go playing computer represent Artificial Intelligence?

There are at least two questions in your question: What are some of the methods used to program the successful go playing program? and Are those methods considered to be artificial ...
user avatar
  • 820
9 votes

What is "backprop"?

'Backprop' is short for 'backpropagation of error' in order to avoid confusion when using backpropagation term. Basically backpropagation refers to the method for computing the gradient of the case-...
user avatar
  • 10k
9 votes
Accepted

Do we have to use CNN for Deep Q Learning?

No. DQN and other deep RL methods work well with fully connected layers. Here's an implementation of DQN which doesn't use CNNs: github.com/keon/deep-q-learning/blob/master/dqn.py DeepMind mostly use ...
user avatar
9 votes
Accepted

What is a recurrent neural network?

Recurrent neural networks (RNNs) are a class of artificial neural network architecture inspired by the cyclical connectivity of neurons in the brain. It uses iterative function loops to store ...
user avatar
  • 699
9 votes
Accepted

What are the differences between an agent and a model?

Agent The other answer defines an agent as a policy (as it's defined in reinforcement learning). However, although this definition is fine for most current purposes, given that currently agents are ...
user avatar
  • 33.8k
8 votes
Accepted

What is "early stopping" in machine learning?

In some iterative learning methods the more iterations you apply the more specific your model becomes about the training set. If there are too many iterations, your model will become too specifically ...
user avatar
  • 381
8 votes

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

In contrast to the philosophical definitions, which rely on terms like "mind" and "think," there are also definitions that hinge on observables. That is, a Strong AI is an AI that understands itself ...
user avatar
8 votes
Accepted

What is the Control Problem?

The Control Problem is, in short, the idea that AI will eventually be much better decision-makers than humans. If we don't set things up correctly beforehand, we won't get a chance to fix it ...
user avatar
8 votes
Accepted

What are hyper-heuristics, and how are they different from meta-heuristics?

TL:DR: Hyper-heuristics are metaheuristics, suited for solving the same kind of optimization problems, but (in principle) affording a "rapid prototyping" approach for non-expert practitioners. In ...
user avatar

Only top scored, non community-wiki answers of a minimum length are eligible