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
1 answer
39 views

Why is the sliding puzzle problem episodic?

Why is the sliding puzzle problem episodic and not sequential? From what I understand, an environment is episodic if each episode is independent and doesn't affect past or future episodes. The actions ...
  • 1
0 votes
0 answers
15 views

How to understand the definition of $\lambda_i$ used in the return estimator proposed in the paper "Human-level Atari 200x faster"?

I'm reading article called "Human-level Atari 200x faster" Agent57 uses Retrace (Munos et al., 2016) to compute return estimates from off-policy data, but we observed that it tends to cut ...
  • 230
0 votes
0 answers
32 views

How to relate the definition for entailment, with soundness and completeness?

Is it fair enough to say for a language model, φ, which makes certain variable A true, and if φ also makes another variable B true, then we can conclude: A ⊨ B And for a certain inference calculus c,...
3 votes
2 answers
111 views

What is the definition of a continuous state/action space?

This question is a result of a discussion with one of my more math-minded friends. When I accidentally mentioned the term continuous state space, he corrected me by saying that I am most probably ...
  • 67
0 votes
1 answer
32 views

Is my neural network working?

I recently just finished programming a neural network in c#, and it seems like it's working. My question is if I'm doing it right. It's a very confusing process so I will explain. Basically every ...
  • 3
0 votes
1 answer
116 views

Hot to calculate Maximum Normalized log Probability for Active Learning with BERT

I have encountered difficulties understanding the calculation of Maximum Normalized Log Probabilities acording to Shen et al.. With n being the sequence length, yi the label of word i. Xij is the ...
0 votes
1 answer
70 views

Autoencoders: Where does the encoder end and the decoder begin?

Consider a simple Autoencoder neural net: ...
1 vote
3 answers
198 views

If a policy is epsilon-greedy, is it technically stochastic?

Even though if exploration doesn't happen, it's deterministic.
  • 95
0 votes
0 answers
47 views

Is the interpretation of the "batch size" in policy gradient algorithms the number of trajectories sampled in VPG and TRPO?

I would like to shore up my interpretation of the concept of "batch size". It is my understanding that in Vanilla Policy Gradients and TRPO, the "batch size" is the number of ...
1 vote
2 answers
52 views

What are all the possible usages of 'multilayer perceptron'?

The term 'multilayer perceptron' has been used in literature in various ways in the literature. I am presenting some of them below As a feed-forward neural network [1]. As a fully connected feed-...
  • 3,451
1 vote
0 answers
32 views

What is an epistemic graph in AI and how is it related to cognitive science?

I found this paper Epistemic graphs for representing and reasoning with positive and negative influences of arguments. I haven't found any definition of or Wikipedia article on epistemic graphs on the ...
0 votes
0 answers
72 views

What is an attractor network?

Surprisingly, this wasn't asked before - at least there was one related question without any answers What is a continuous-attractor neural network?. So, what is an attractor network, and why should ...
  • 135
2 votes
2 answers
1k views

What does it mean by "gradient flow" in the context of neural networks?

Several research papers and textbooks (e.g. this) contain the phrase "gradient flow" in the context of neural networks. I am confused about whether it has any rigorous and formal way of ...
  • 3,451
1 vote
1 answer
118 views

What exactly is data augmentation?

Data augmentation is useful in training. But, I am not sure when can a modification applied to data can be called data augmentation. Suppose a technique is applied to the instances of a dataset and ...
  • 3,451
0 votes
1 answer
701 views

What is the definition of a 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 ...
  • 3,451
0 votes
1 answer
106 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 (...
  • 3,451
3 votes
2 answers
426 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 ...
  • 3,451
1 vote
1 answer
68 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 ...
  • 3,451
3 votes
1 answer
88 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
0 answers
64 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. $$ \...
  • 3,451
1 vote
0 answers
59 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 ...
  • 3,451
0 votes
2 answers
182 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?
  • 3,451
1 vote
0 answers
104 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 $$Cov[X, Y] = \mathbb{E}[(X - \mathbb{E}[X])(Y-\mathbb{E}[Y])]$$...
  • 3,451
0 votes
1 answer
33 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 ...
  • 3,451
0 votes
2 answers
74 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 ...
  • 3,451
2 votes
2 answers
90 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 ...
  • 323
2 votes
1 answer
417 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&...
  • 3,451
0 votes
1 answer
251 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 ...
  • 3,451
0 votes
2 answers
752 views

What is meant by an axis of a tensor?

Tensor is an ordered collection of elements. The elements are generally real numbers. Tensors are used in deep learning for storing data. There is a wide usage of the word "axis" related to ...
  • 3,451
1 vote
1 answer
61 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 ...
  • 3,451
1 vote
0 answers
40 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 ...
  • 3,451
1 vote
0 answers
35 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 ...
  • 201
3 votes
2 answers
158 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 ...
  • 3,451
-1 votes
1 answer
52 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
1 answer
61 views

Fitting a Gaussian distribution into another distribution

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 ...
4 votes
2 answers
130 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 ...
6 votes
3 answers
2k 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
2 answers
205 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 ...
  • 36.3k
2 votes
3 answers
475 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 ...
  • 36.3k
1 vote
0 answers
64 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 ...
  • 35
3 votes
1 answer
73 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 ...
  • 133
2 votes
0 answers
113 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 $T$ ...
  • 287
8 votes
1 answer
2k 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 ...
5 votes
3 answers
222 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 ...
  • 255
4 votes
1 answer
159 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?
  • 171
3 votes
1 answer
120 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?
  • 1,213
2 votes
1 answer
4k 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 ...
  • 3,451
9 votes
3 answers
2k 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 ...
  • 2,589
0 votes
1 answer
70 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
0 answers
50 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 ...
  • 11