Questions tagged [definitions]

For questions about the definition of terms used in artificial intelligence research and development, including the definition of intelligence, algorithms, jargon, principles, methodologies, mathematical terms, concepts, topologies, architectures, designs, jargon, and AI domains such as robotics, network training, or automated vehicles.

Filter by
Sorted by
Tagged with
7
votes
1answer
437 views

Can neural networks with a sigmoid as the activation function of the output layer approximate continuous functions?

Neural networks are commonly used for classification tasks, in fact from this post it seems like that's where they shine brightest. However, when we want to classify using neural networks, we often ...
14
votes
5answers
3k views

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

It's an idea I heard a while back but couldn't remember the name of. It involves the existence and development of an AI that will eventually rule the world and that if you don't fund or progress the ...
2
votes
2answers
73 views

Can you provide some pseudocode examples of what constitutes an AI?

After years of learning, I still can't understand what is considered to be an AI. What are the requirements for an algorithm to constitute Artificial Intelligence? Can you provide pseudocode examples ...
1
vote
1answer
41 views

What is teacher forcing?

In the paper Neural Programmer-Interpreters, the authors use the teacher forcing technique, but what exactly is it?
1
vote
1answer
34 views

What is an end-to-end AI project?

I often read about the so-called end-to-end AI (or analytics) projects, but I couldn't find a definition of it. What is an end-to-end AI project? Can someone explain what is meant/expected when ...
3
votes
0answers
32 views

How exactly does self-play work, and how does it relate to MCTS?

I am working towards using RL to create an AI for a two-player, hidden-information, a turn-based board game. I have just finished David Silver's RL course and Denny Britz's coding exercises, and so am ...
2
votes
1answer
47 views

How does crossover work in a genetic algorithm?

If I had the weights of a certain number of "parents" that I wanted to crossbreed, and I used whatever method to pick out the "best parents" (I used a roulette wheel option, if that's any relevant), ...
1
vote
1answer
50 views

Is the following statement about neural networks overclaimed?

Is the following statement about neural networks overclaimed? Neural networks are iterative methods that minimize a loss function defined on the output layer of neurons. I wrote this statement in ...
5
votes
1answer
228 views

What is the mathematical definition of an activation function?

What is the mathematical definition of an activation function to be used in a neural network? So far I did not find a precise one, summarizing which criterions (e.g. monotonicity, differentiability, ...
1
vote
1answer
109 views

What is a cascaded convolutional neural network?

For a project I am doing, I found the paper Face Alignment in Full Pose Range: A 3D Total Solution. It is using a cascaded convolutional neural network, but I wasn't able to find the original paper ...
2
votes
1answer
80 views

List of currently available artificial general intelligence systems

I wished to compile a (somewhat) comprehensive list of companies and organizations that are developing "Artificial General Intelligence (AGI)" or "strong AI" systems, their products and purported ...
2
votes
1answer
83 views

How to define the “Pre-Processing” in machine learning?

Is every process1 that is done on the data before we train the model is always called the pre-processing part? Or are there some processes which are not included? 1"Every process" is includes data ...
4
votes
1answer
68 views

When exactly is a model considered over-parameterized?

When exactly is a model considered over-parameterized? There are some recent researches in Deep Learning about the role of over-parameterization toward generalization, so it would be nice if I can ...
0
votes
1answer
74 views

What are the characteristics of a deep learning AI?

I have experience in making several Artificial Neural Networks and some programs which may be classified as an Artificial Intelligence by using Tensorflow.js and Brain.js. In order to produce ...
3
votes
1answer
375 views

What does the Markov assumption say about the history of state sequences?

Does the Markov assumption say that the conditional probability of the next state only depends on the current state or does it say that the conditional probability depends on a fixed finite number of ...
3
votes
2answers
440 views

What is a “surrogate model”?

In the following paragraph from the book Automated Machine Learning: Methods, Systems, Challenges (by Frank Hutter et al.) In this section we first give a brief introduction to Bayesian ...
4
votes
1answer
57 views

What do the subscripts mean in $N_{t,n,\sigma,L}$?

A neural network can apparently be denoted as $N_{t,n,\sigma,L}$. What do these subscripts $t, n, \sigma$ and $L$ mean? Could you link me to a paper, article or webpage with an explanation for this?
1
vote
1answer
68 views

What is the difference between the definition of a stationary policy in reinforcement learning and contextual bandit?

A stationary policy is a function that maps a state to a probability distribution of actions. In a contextual bandit problem, a state itself does not include the history. But in a reinforcement ...
2
votes
1answer
56 views

In the graph search version of A*, can I stop the search the first time I encounter the goal node?

I am going through Russel and Norvig's Artificial Intelligence: A Modern Approach (3rd edition). I was reading the part regarding the A* algorithm A* graph search version is optimal when heuristic ...
3
votes
1answer
58 views

What is a non-starving policy in reinforcement learning?

In the paper, Eligibility Traces for off-Policy Policy Evaluation (2010), by Doina Precup et al., mentioned the term "non-starving" many times. The specific use of the term was like "non-starving ...
2
votes
2answers
98 views

Is unsupervised learning a branch of AI?

From Artificial Intelligence: A Modern Approach, a book by Stuart Russell and Peter Norvig, this is the definition of AI: We define AI as the study of agents that receive percepts from the ...
3
votes
1answer
40 views

Is a state that includes only the past n-step price records partially observable?

I'm currently working on a project to make an DQN agent that decides whether to charge or discharge an electric vehicle according to hourly changing price to sell or buy. The price pattern also varies ...
1
vote
1answer
178 views

What is an identity recurrent neural network?

What is an identity recurrent neural network (IRNN)? What is the difference between an IRNN and RNN?
0
votes
0answers
36 views

Pooling vs Subsampling: Multiple Definitions?

I have seen people using pooling and subsampling synonymously. I have also seen people use them as different processes. I am not sure though if I have correctly inferred what they mean, when they use ...
2
votes
0answers
52 views

What is the meaning of the words 'bias' and 'variance' in RL?

In algorithms like MC/TD (tabular value approximation) two of the metrics used to measure their performance are the bias and the variance. What do these terms mean? And which characteristic of the ...
3
votes
1answer
73 views

Clarification on definition of convolution: Is adding the Frobenius inner products between filter and input part of convolution or a separate step?

From the literature I have read so far, it is not clear how exactly the convolution operation is defined. It seems people use two different definitions: Let us assume we are given an $n_w \times n_h \...
1
vote
1answer
24 views

Why are activation functions independent layers in CNNs rather than part of convolutional layers?

I have been reading up on CNNs. One of the different confusing things has been that people always talk of normalization layers. A common normalization layer is a ReLU layer. But I never encountered an ...
3
votes
2answers
47 views

Are feature maps merged or are they passed on as they are?

I am unsure about the following parts of the architecture and mechanics of convolution layers in CNNs. Possibly, this is implementation-dependent though. First question: Say I have 2 convolution ...
0
votes
0answers
29 views

Can simple tools like the Pascaline be considered artificial intelligence? [duplicate]

Question in Brief The popular usage (I'm not sure of exact technical usage), limits the term "artificial intelligence" to only the "high-end" tasks; as if AI has something limited to "high-end". But "...
2
votes
2answers
55 views

Can non-Markov environments also be deterministic?

The definition of deterministic environment I am familiar with goes as follows: The next state of the agent depends only on the current state and the action chosen by the agent. By exclusion, ...
2
votes
0answers
85 views

What is a conditional random field?

I new in machine learning, especially in Conditional Random Fields (CRF). I have read several articles and papers and in there is always associated with HMM and sequences classification. I don't ...
3
votes
1answer
66 views

Which models accept numerical parameters and produce a numerical output?

I need a model that will take in a few numerical parameters, and give back a numerical answer (Context: predicting a slope based on environmental factors without having to actually take measurements ...
0
votes
0answers
18 views

Is learning from demonstration equal to plan recognition?

The amount of literature about “Learning from demonstration” (LfD) is huge. The idea, in short, is that a human operator is moving the robot's arm slowly, the motion gets recorded, and after pressing ...
1
vote
1answer
758 views

What is an agent in Artificial Intelligence?

While studying artificial intelligence, I have often encountered the term "agent" (often autonomous, intelligent). For instance, in fields such as Reinforcement Learning, Multi-Agent Systems, Game ...
7
votes
1answer
3k 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?
0
votes
1answer
87 views

What is machine learning?

What is the definition of machine learning? What are the advantages of machine learning?
2
votes
1answer
42 views

What is the prediction accuracy?

In simple words, what is the prediction accuracy? What is it based on? How does it help? When is it used?
2
votes
2answers
155 views

What is the difference between Sentiment Analysis and Emotion Recognition?

I found Sentiment Analysis and Emotion Recognition as two different categories on paperswithcode.com. Should both be the same as my understanding? If not what's the difference?
1
vote
1answer
580 views

What is a temporal feature?

What is a temporal feature, what features make something temporal in nature? Is this problem agnostic? How does it change from different fields of study?
3
votes
1answer
62 views

What is local consistency in constraint satisfaction problems?

In the Constraint Propagation in CSP, it is often stated that pre-processing can solve the whole problem, so no search is required at all. And the key idea is local consistency. What does this ...
6
votes
2answers
1k views

What algorithms are considered reinforcement learning algorithms?

What are the areas that belong to the Reinforcement Learning? TD(0), Q-Learning and SARSA are all temporal-difference algorithms, which belong to the reinforcement learning area, but is there more to ...
4
votes
3answers
185 views

What is an artificial neural network?

What is an artificial neural network in artificial intelligence? It is apparently used to find patterns in data and it is loosely inspired by human neural networks.
2
votes
1answer
123 views

When is content-based more appropriate than collaborative filtering?

I know the difference between content-based and collaborative filtering approach in recommender systems. I also know some of the articles said collaborative filtering have some advantages than content-...
3
votes
0answers
75 views

What is a generalized MDP?

What is a generalized MDP? How is it different than a "regular" MDP? How does it generalise the notion of an MDP? Why do we need a generalised MDP? Do generalised MDPs have some practical usefulness ...
4
votes
3answers
392 views

Do we have to use CNN for Deep Q Learning?

I read top articles on Google Search about Deep Q-Learning: https://medium.freecodecamp.org/an-introduction-to-deep-q-learning-lets-play-doom-54d02d8017d8 https://skymind.ai/wiki/deep-reinforcement-...
1
vote
0answers
125 views

What is a graph neural network?

What is a graph neural network (GNN)? How is a GNN different from a NN? How exactly is a GNN related to graphs? What are the components of a GNN? What are the inputs and outputs of GNNs? How can ...
9
votes
2answers
1k views

What is geometric deep learning?

What is geometric deep learning (GDL)? How is it different from deep learning? Why do we need GDL? What are some applications of GDL?
2
votes
2answers
65 views

Is the definition of machine learning by Mitchell in his book “Machine Learning” valid?

The definition machine learning is as follows: A computer program is said to learn from experience E with respect to some task T and performance measure P, if its performance at task T, as ...
3
votes
1answer
82 views

What is the relation between a policy which is the solution to a MDP and a policy like $\epsilon$-greedy?

In the context of reinforcement learning, a policy, $\pi$, is often defined as a function from the space of states, $\mathcal{S}$, to the space of actions, $\mathcal{A}$, that is, $\pi : \mathcal{S} \...
4
votes
2answers
78 views

How are the reward functions $R(s)$, $R(s, a)$ and $R(s, a, s')$ equivalent?

In this video, the lecturer states that $R(s)$, $R(s, a)$ and $R(s, a, s')$ are equivalent representations of the reward function. Intuitively, this is the case, according to the same lecturer, ...