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
0
votes
0answers
29 views

What is the recurrent matrix in a recurrent neural network?

What is the recurrent matrix in a recurrent neural network? Is it the same thing with the transition matrix and the hidden-to-hidden weight matrix?
2
votes
0answers
27 views

What exactly does meta-learning in reinforcement learning setting mean?

We can use DDPG to train agents to stack objects. And stacking objects can be viewed as first grasping followed by pick and place. In this context, how does meta-reinforcement learning fit? Does it ...
2
votes
0answers
30 views

What is the return-to-go in reinforcement learning?

In reinforcement learning, the return is defined as some function of the rewards. For example, you can have the discounted return, where you multiply the rewards received at later time steps by ...
2
votes
1answer
51 views

What's the difference between estimation and approximation error?

I'm unable to find online, or understand from context - the difference between estimation error and approximation error in the context of machine learning (and, specifically, reinforcement learning). ...
2
votes
1answer
51 views

What is the difference between parametric and non-parametric models?

A model can be classified as parametric or non-parametric. How are models classified as parametric and non-parametric models? What is the difference between the two approaches?
2
votes
1answer
31 views

What's the threshold to call something 'machine learning'?

For example, if I use some iterative solvers to find a solution to a non-linear least squares problem, is that already considered machine learning?
2
votes
1answer
49 views

What are proxy reward functions?

The understanding I have is that they somehow adjust the objective to make it easier to meet, without changing the reward function. ... the observed proxy reward function is the approximate solution ...
4
votes
1answer
94 views

What is eager learning and lazy learning?

What is the difference between eager learning and lazy learning? How does eager learning or lazy learning help me build a neural network system? And how can I use it for any target function?
0
votes
1answer
77 views

What is Cognitive Intelligence?

Similarly to the question, What is artificial intelligence? Cognitive Intelligence, as well as being a part of Artificial Intelligence, is an area that mainly covers the technology and tools that ...
1
vote
1answer
69 views

What is the difference between artificial neural network (ANN) and deep learning?

I have read many mixed definitions around these two terms. For example, is it right to say deep learning is any ANN with more than two hidden layers? What are formal definitions for these two?
1
vote
2answers
400 views

What is the Turing test?

I'm looking for intuition in simple words but also some simple insights (I don't know if the latter is possible). Can anybody shed some light on the Turing test?
2
votes
2answers
148 views

What are the main algorithms used in computer vision?

Nowadays, CV has really achieved great performance in many different areas. However, it is not clear what a CV algorithm is. What are some examples of CV algorithms that are commonly used nowadays and ...
0
votes
1answer
81 views

What is a convolutional neural network?

Given that this question has not yet been asked on this site, although similar questions have already been asked in the past (e.g. here or here), what is essentially a convolutional neural network (...
5
votes
3answers
884 views

What is Reinforcement Learning?

What is the cleanest, easiest way to explain someone who is a non-STEM work colleague the concept of Reinforcement Learning? What are the main ideas behind Reinforcement Learning?
5
votes
1answer
183 views

How do I recognise a bandit problem?

I'm having difficulty understanding the distinction between a bandit problem and a non-bandit problem. An example of the bandit problem is an agent playing $n$ slot machines with the goal of ...
3
votes
1answer
158 views

How do we express $q_\pi(s,a)$ as a function of $p(s',r|s,a)$ and $v_\pi(s)$?

The task (exercise 3.13 in the RL book by Sutton and Barto) is to express $q_\pi(s,a)$ as a function of $p(s',r|s,a)$ and $v_\pi(s)$. $q_\pi(s,a)$ is the action-value function, that states how good ...
2
votes
1answer
45 views

Can the agent wait until the end of the episode to determine the reward in SARSA?

From Sutton and Barto's book Reinforcement Learning (Adaptive Computation and Machine Learning series) (p. 99), the following definition for first-visit MC prediction, for estimating $V \sim V_\pi$ is ...
2
votes
2answers
186 views

Why is the policy not a part of the MDP definition?

I'm reading an article on reinforcement learning, and I don't understand why the agent's policy $\pi$ is not part of definition of Markov Decision process(MDP): Bu, Lucian, Robert Babu, and Bart De ...
0
votes
1answer
88 views

Is my understanding of how AI works correct?

In my discussion over my question on Math SE, I explained to a user, how I think AI works, I wrote that with the sigmoid(logistic) function, features of a data set are identified, many such iterations ...
2
votes
1answer
71 views

In what RL algorithm category is MiniMax?

Q-learning is a temporal-difference method and Monte Carlo tree search is a Monte Carlo method. In what category is MiniMax?
4
votes
1answer
76 views

Would you categorize policy iteration as an actor-critic reinforcement learning approach?

One way of understanding the difference between value function approaches, policy approaches and actor-critic approaches in reinforcement learning is the following: A critic explicitly models a value ...
3
votes
1answer
44 views

Is the test time the phase when the model's accuracy is calculated with test data set?

When papers talk about the "test time", does this mean the phase when the model is passed with new data instances to derive the accuracy of the test data set? Or is "test time" the phase when the ...
1
vote
0answers
51 views

What's the meaning of the Jaccard decay and the Jaccard recall? [closed]

For reference, see: Jaccard decay, Jaccard recall, and class-agnostic binary segmentation (SE:CS) I know the meaning of the Jaccard index and the formula associated to it, but when it comes to Jaccard ...
2
votes
1answer
53 views

What are preferences and preference functions in multi-objective reinforcement learning?

In RL (reinforcement learning) or MARL (multi-agent reinforcement learning), we have the usual tuple: (state, action, transition_probabilities, reward, next_state) ...
1
vote
1answer
42 views

What is generalized policy iteration?

I am reading Sutton and Barto's material now. I know value iteration, which is an iterative algorithm taking the maximum value of adjacent states, and policy iteration. But what is generalized policy ...
7
votes
1answer
532 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
162 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
84 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
47 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
45 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
65 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
56 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 ...
6
votes
1answer
290 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
657 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
118 views

Which AGI systems have already been implemented and tested?

I wish to compile a (somewhat) comprehensive list of AGI systems that have actually been created and tested (to whatever degrees of success) instead of those that simply advertise they are going to '...
2
votes
1answer
95 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
114 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
93 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
652 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
1k 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
58 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
97 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
70 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
67 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
107 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
42 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
321 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
44 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
62 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 ...