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
3 views

What is the definition for trace of a tensor?

Tensor is a multi-dimensional ordered collection of elements, which is used in deep learning to store and process data as well as intermediate steps. We are aware of the trace of a two-dimensional ...
0
votes
1answer
49 views

What is the rigorous and formal definition for the direction pointed by a gradient?

Consider the following definition of derivative from the chapter named Vector Calculus from the test book titled Mathematics for Machine Learning by Marc Peter Deisenroth et al. Definition 5.2 (...
4
votes
2answers
412 views

When can I call an entity a hyperparameter?

As per my knowledge, any entity that is learnable by a training algorithm can be called a parameter. Weights of a neural network are called parameters because of this reason only. But I have doubts ...
1
vote
1answer
25 views

What is meant by sub-region of an image?

Consider the following sentences from the research paper titled PatternNet: Visual Pattern Mining with Deep Neural Network by Hongzhi Li et al. The value of each pixel in a feature map is the ...
3
votes
1answer
58 views

In reinforcement learning, why are policies defined as functions of states and not observations?

I am new to RL and I am following Sutton & Barto's book. My doubt is, when we talk about the policy of our agent, we say it is the probability of taking some action $a$ given the state $s$. ...
1
vote
0answers
40 views

Can I call any function a signal?

While reading the Notation of the paper titled Geometric Deep Learning Grids, Groups, Graphs, Geodesics, and Gauges, I came across the following notations. $$ \...
1
vote
0answers
47 views

What are the definitions for the content and style of an image without using deep neural network?

In deep learning, an image is said to contain two types of features. One is the content of the image and the other is the style of the image. Deep neural networks are generally used to obtain both ...
0
votes
0answers
36 views

What are mathematically the factors of variation in deep learning?

The following paragraph from an answer tells us about factors of variation Factors of variation are some factors which determine varieties in observed data. If that factors change, the behaviour of ...
0
votes
2answers
97 views

What is the formal definition for manifold in artificial intelligence?

We come across the word "manifold" in artificial intelligence, especially in the domains where learning is done based on data instances. What is the formal definition for manifold?
1
vote
0answers
60 views

What is meant by correlation structure?

I know only about the Pearson's correlation coefficient in literature. Covariance between two random variables $X$ and $Y$ is defined as $$Cov[X, Y] = \mathbb{E}[(X - \mathbb{E}[X])(Y-\mathbb{E}[Y])]$$...
0
votes
1answer
19 views

Is there any difference between the phrases "text representation" and "text feature representation"?

Text representation, in simple words, is representing text in sensible numeric form. You can read in detail from the following paragraph Text representation is one of the fundamental problems in text ...
0
votes
2answers
57 views

What is the definition of "confidence interval" around a (complicated) function?

Consider the following excerpt from Chapter 5: Machine Learning Basics from the book titled Deep Learning (by Aaron Courville et al.) Machine learning is essentially a form of applied statistics with ...
2
votes
2answers
72 views

Explaining AI to Non-Technical Individuals

How does one approach proposing AI to management? This is something I have struggled with for a long time. I want to implement AI toward a specific problem in my place of work. My supervisors are ...
2
votes
1answer
353 views

What exactly is a Parzen?

I came across the term "Parzen" while reading the research paper titled Generative Adversarial Nets. It has been used in the research paper in two contexts. #1: In phrase "Parzen window&...
0
votes
1answer
48 views

Is my understanding on "smooth approximation" correct?

Consider the following details regarding Softplus activation function $$\text{Softplus}(x) = \dfrac{\log(1+e^{\beta x})}{\beta}$$ SoftPlus is a smooth approximation to the ReLU function and can be ...
1
vote
1answer
31 views

Does "fusion" in "feature fusion" has any formal definition?

I encountered the phrase "fusing features" several times in the literature. I am providing an excerpt from a research paper to provide context for usage of the word fusion. The reason is ...
1
vote
0answers
34 views

What is meant by "Zero-Shot Visual Recognition"?

Many recent research papers contain the phrase "Zero-Shot Visual Recognition". What exactly is meant by zero-shot visual recognition? Does the task need only images or also the other data ...
0
votes
0answers
19 views

How should we interpret "common coarsening" in this proof of the uniqueness of coarsest bisimulation?

On page 4 of this pdf in a theoretical RL course, we have a proof of the uniquness of the coarsest bisimulation. A bisimulation $\phi$ is a mapping from states $s \in\mathcal{S}$ to abstract states $\...
2
votes
0answers
30 views

Is the formula $\frac {1}{s}\sum _{j=1}^{s}|d_{j}-y_{j}(t)|$ the correct form of 0-1 loss function, in the context of Perceptron?

Per page 7 of this MIT lecture notes, the original single-layer Perceptron uses 0-1 loss function. Wikipedia uses $${\displaystyle {\frac {1}{s}}\sum _{j=1}^{s}|d_{j}-y_{j}(t)|} \tag{1}$$ to denote ...
3
votes
2answers
83 views

Why do we commonly use the $\log$ to squash frequencies?

Term frequency and inverse document frequency are well-known terms in information retrieval. I am presenting the definitions for both from p:12,13 of Vector Semantics and Embeddings On term frequency ...
0
votes
1answer
45 views

how to go from mathematical problem to neural network (and back)?

I am a little confused on how, you can find online papers that describe complex Machine Learning formulas in a mathematical/probabilistic way, and, in the other hands, easy tutorials that teach you ...
0
votes
1answer
37 views

Fitting a gaussian distribution into another distribution - and correlation with Machine Learning

Assume we have two vectors, containing random samples (maybe audio data?). Their distribution can be approximated to a normal distribution, so we can calculate their mean and standard deviation. I am ...
3
votes
1answer
42 views

What makes a transformer a transformer?

Transformers are modified heavily in recent research. But what exactly makes a transformer a transformer? What is the core part of a transformer? Is it the self-attention, the parallelism, or ...
4
votes
3answers
296 views

What exactly are partially observable environments?

I have trouble understanding the meaning of partially observable environments. Here's my doubt. According to what I understand, the state of the environment is what precisely determines the next state ...
1
vote
2answers
119 views

Why was the VC dimension not defined for all configurations of $d$ points?

Let's start with a typical definition of the VC dimension (as described in this book) Definition $3.10$ (VC-dimension) The $V C$ -dimension of a hypothesis set $\mathcal{H}$ is the size of the ...
2
votes
3answers
120 views

How would you intuitively but rigorously explain what the VC dimension is?

The VC dimension is a very important concept in computational/statistical learning theory. However, the first time you read its definition, you may not immediately understand what it really represents ...
1
vote
0answers
46 views

What is dynamic data sampling in federated learning?

I am trying to learn about Federated Learning (FL), but I have a question. What is dynamic data sampling in FL? Cai, Lingshuang, et al. "Dynamic Sample Selection for Federated Learning with ...
3
votes
1answer
55 views

Is there a clear distinction between Artificial Intelligence and running a sequential program?

Artificial Intelligence (AI) is often defined as a machine that is intelligent, or one that can think rationally. From a high-level perspective, things like self-driving car or Alpha-Go can easily be ...
2
votes
0answers
59 views

Is there any reasonable notion of regret for infinite horizon discounted MDPs?

I am thinking about episodic MDPs. Usually, in episodic MDPs, it seems that we have a finite fixed horizon per episode and no discount factor. Then, a very intuitive notion of regret after $T$ ...
7
votes
1answer
545 views

What is ergodicity in a Markov Decision Process (MDP)?

I have read about the concept of ergodicity on the safe RL paper by Moldovan (section 3.2) and the RL book by Sutton (chapter 10.3, 2nd paragraph). The first one says that "a belief over MDPs is ...
4
votes
2answers
67 views

How widely accepted is the definition of intelligence by Marcus Hutter & Shane Legg?

I came across several papers by M. Hutter & S. Legg. Especially this one: Universal Intelligence: A Definition of Machine Intelligence, Shane Legg, Marcus Hutter Given that it was published back ...
3
votes
1answer
83 views

How to define machine learning to cover clustering, classification, and regression?

How to define machine learning to cover clustering, classification, and regression? What unites these problems?
3
votes
1answer
74 views

What is Federated Learning?

How would you explain Federated Learning in simple layman terms for a non-STEM person? What are the main ideas behind Federated Learning?
3
votes
1answer
998 views

What is the definition of the hinge loss function?

I came across the hinge loss function for training a neural network model, but I did not know the analytical form for the same. I can write the mean squared error loss function (which is more often ...
8
votes
3answers
1k views

What are the differences between an agent and a model?

In the context of Artificial Intelligence, sometimes people use the word "agent" and sometimes use the word "model" to refer to the output of the whole "AI-process". For ...
0
votes
1answer
65 views

Can AI be understood as a generalized statistics tool? [duplicate]

I am a (soon-to-become, to be honest) theoretical physicist. I want to learn a bit about AI. So as you know in physics we develop theories based on as few and as simple basic equations as possible ...
1
vote
0answers
38 views

What is the definition of pre-training?

I want to pre-train a model (combined by two popular modules A and B, and both are large blocks), then fine-tune it on downstream tasks. What if for the weight initialization for pre-training, module ...
1
vote
1answer
110 views

What are support values in a support vector machine?

I started reading up on SVM and very little is defined of what are support values. I reckon it's they are denoted as $\alpha$ in most formulations.
2
votes
1answer
86 views

In the machine learning literature, what does it mean to say that something is "embedded" in some space?

In the machine learning literature, I often see it said that something is "embedded" in some space. For instance, that something is "embedded" in feature space, or that our data ...
3
votes
4answers
649 views

What is the fundamental difference between an ML model and a function?

A model can be roughly defined as any design that is able to solve an ML task. Examples of models are the neural network, decision tree, Markov network, etc. A function can be defined as a set of ...
5
votes
2answers
413 views

What is the Bellman Equation actually telling?

What does the Bellman equation actually say? And are there many flavours of that? I get a little confused when I look for the Bellman equation, because I feel like people are telling slightly ...
2
votes
1answer
47 views

Why is it useful to define the return as the sum of the rewards from time $t$ onward rather than up to $t$?

Why is it useful to define the return as the sum of the rewards from time $t$ onward rather than up to $t$? The return for an MDP is usually defined as $$G_t=R_{t+1}+R_{t+2}+ \dots +R_T$$ Why is this ...
1
vote
1answer
76 views

Is it okay to think of any dataset in artificial intelligence as a mathematical set?

A dataset is a collection of data points. It is known that the data points in the dataset can repeat. And the repetition does matter for building AI models. So, why does the word dataset contain the ...
4
votes
1answer
207 views

Is case-based reasoning a machine learning technique?

A few years ago when I was in university, I had implemented (for my final year project) an Itinerary Planning System, which incorporates an AI technique called "case-based reasoning". Is ...
2
votes
0answers
36 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
139 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 ...
4
votes
1answer
95 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?
4
votes
2answers
153 views

Why is regret so defined in MABs?

Consider a multi-armed bandit(MAB). There are $k$ arms, with reward distributions $R_i$ where $1 \leq i \leq k$. Let $\mu_i$ denote the mean of the $i^{th}$ distribution. If we run the multi-armed ...
2
votes
1answer
42 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
144 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 ...