Questions tagged [artificial-intelligence]
For questions about artificial intelligence, the intelligence of machines and robots and the branch of computer science that aims to create it.
1
vote
1answer
26 views
how is local minima possible in gradient descent?
gradient descent works on the equation of mean squared error, which is an equation of a parabola y=x^2
we often say weight adjustment in a neural network by ...
-1
votes
1answer
17 views
Markov Decision Process - Discounted return
I was reading this article about Discounted return (in the context of MDP): http://deeplizard.com/learn/video/a-SnJtmBtyA
I got the section:
...
0
votes
0answers
19 views
Inference can be the goal of an unsupervised learning method?
I am new to machine learning, and I am reading a pair of machine learning books. Those references talk about 2 different learning approaches: Prediction and inference, I understand the difference ...
1
vote
1answer
45 views
Policy gradient reinforcement learning for continuous state and action space
I am a novice in the field of machine learning, I have a moderate level understanding of linear/non-linear regression, support vector machines, neural networks, and q-learning (for discrete finite ...
0
votes
1answer
18 views
Different order of insertion - different Bayesian network ? how to prove formally?
I have some Bayesian network which i constructed from some data, say it consists of nodes A, B, C and D and that was the initial order of insertion.
If i ...
1
vote
2answers
42 views
First Order Logic to CNF for Knowledge Base
I am doing some Homework for an Artificial Intelligence Course, we are covering some First Order Logic and Conjuctive Normal Form.
Here are the questions that I have to answer that I am having ...
1
vote
0answers
31 views
Variable transformation for training a machine learning model
Suppose you have a train set $\mathbf{T}$ and you want to train some Machine Learning models. Each row of $\mathbf{T}$ consists in a set(vector) of attributes or variables $\mathbf{x} = (x_1, x_2...)$ ...
2
votes
1answer
31 views
MGU - most general unifier for skolem functions?
I have trouble understanding MGU for functions, especially skolem functions.
Is it correct that in order to find MGU for 2 functions, say f(x) and g(y) then they ...
-1
votes
0answers
12 views
Minimal Explanations for an observation in a given knowledge base
Given the following knowledge base:
a := e
b := f
a := f
b := g
c := g
c := h
d := h
false := h & g
false := i & a
assumables: e,f,g,h
And the following ...
2
votes
0answers
19 views
Derivation Contrastive Divergence
I am trying to follow the original paper of GE Hinton: Training Products of Experts by Minimizing Contrastive Divergence
However I can't verify equation (5) where he says:
$$
-\frac{\partial}{\...
4
votes
0answers
63 views
Algebra & Artificial Intelligence (AI)
Artificial intelligence, especially deep learning & neural networks for image processing and classfication, are related to statistics and physics e.g. as decribed in below papers.
Statistics and ...
2
votes
1answer
165 views
Category Theory & Artificial Intelligence (AI)
Category theory turns out to be useful in more and more areas.
(see e.g. MSE - Category Theory & Biology)
Question. Does anyeone know of some connection of category theory to (convolutional) ...
3
votes
1answer
58 views
Are neural networks with bounded parameters a compact subset of the Banach space of continuous functions?
Let $d, n \in \mathbb{N}$. Moreover, let $D \subset \mathbb{R}^d$ be compact and denote with
$\mathcal{C}(D, \mathbb{R}^n) $
the set of continuous functions from $D$ to $\mathbb{R}^n$. Then $\mathcal{...
1
vote
1answer
33 views
What is the output in a RNN?
I have recently been looking for some information about recurrent neural networks. Some people use a layer between the hidden state and the output and other ones use the hidden state as output.
What ...
0
votes
0answers
39 views
What's going on in this sum?
This is part of a slope calculation example to update the new weight of a neural network from the slope. From a Deep Learning course on DataCamp
My math is a bit dodgy and what I don't understand is ...
0
votes
1answer
31 views
reverse mapping of SVM kernel into original feature space
I am experimenting with support vector machines (SVM) following this book
Without a kernel, it is very easy to "summarize" the SVM optimal solution, as you only need the separator hyperplane w, equal ...
0
votes
0answers
16 views
What is the meaning of stochastic sampling?
I came across this term in the context of Kernel Methods for Supervised Learning.
Subsampling is the selection of a subset from the training set. But what is stochastic subsampling, I understand that ...
1
vote
1answer
108 views
Turn into Proposition logic
I am new to logic. I am suffering to turn one of the following sentences from normal form into propositional logic. Paragraph as follows:
...
2
votes
0answers
44 views
What courses should I take in my Masters for PhD in mathematics - artificial intelligence? [closed]
I am currently enrolled in a masters programme in mathematics and I am taking mostly courses in mathematical statistics, but also dynamical systems and analysis. And I'm wondering if I want to go ...
0
votes
0answers
23 views
Is it possible to output vectors/scalars from a neural network that are of a different type than the input
I have just begun researching convolutional neural networks on images and I see that they are useful for processes such as feature recognition and de noising etc. as they apply transformations to the ...
1
vote
1answer
24 views
Back propagation equation proof
I am trying to prove this equation (from the backpropagation equations in AI).
$$\frac{\partial C}{\partial b_j^l} = \delta_j^l$$
C is the cost function: $C = \frac{1}{2}||y - a^L||^2$
Where the ...
0
votes
0answers
23 views
Matrix valued function theory for neural networks
Is there matrix valued function theory for neural networks (for optimal learning of weights and biases, for optimal meta-learning of architecture, for learning rate estimation)? I have found only ...
2
votes
0answers
85 views
Project ideas on Chaos theory, Cellular Automata, Fractals, Games, IA [closed]
I'm a computer science student and I need to find a final year project. What interests me the most is Chaos, IA, Games, Fractals, CA..
Something I liked was the chaos theory within sudoku.
The ...
0
votes
0answers
54 views
Applications of Stochastic Dynamical Systems in Artificial Intelligence
It is my first post here but I have come to ask a question that will, hopefully, clear the ambiguity I have regarding the subject.
A bit of a background about myself - I am a physics undergraduate ...
1
vote
0answers
89 views
What are some current best practices for function approximation using neural networks?
There are lots of guides out there for current best practices for using neural networks for classification tasks. However, these guides don't always apply to function approximation.
What are some of ...
1
vote
0answers
42 views
Machine of maximum number of support vectors (SVM)?
I have learned a thing or two about Support Vector Machines (SVM) and it seems to me that maximum margin machines are popular. I came to wonder if there exist any flavour of SVM which not only strive ...
0
votes
1answer
47 views
How to convert an English sentence that contains “can't take more than 2” into predicate calculus sentence? [closed]
The example is :
A student can’t take more than 2 courses with the same instructor
0
votes
1answer
43 views
What is the set of models of the empty set?
We have that :
$Mod (\emptyset) = \{ I \in Int_{At} / I \vDash \emptyset \}.$
My question is, what is the set of interpretations that satisfty the empty set?
3
votes
0answers
68 views
Why is the Error surface for a 2 input neural network with 2 weights a parabolic bowl
I am new to machine learning and AI in general and had a quick question regarding the error function surface regarding a simple neural net:
2 input neural net
After reading the following wiki: https:/...
1
vote
1answer
206 views
Sample covariance matrix notation
I do not understand this notation for the sample covariance matrix (from Artificial Intelligence: A Modern Approach, Peter Norvig and Stuart J. Russell, Section 20.3, EM algorithm):
$\Sigma_{i} = \...
0
votes
0answers
76 views
Using ANNs to solve Polynomials
Is it possible to train a neural network to solve a polynomial equation? What about any non-linear single variable equation? Has it been done before
I am thinking of training a neural network to ...
0
votes
1answer
46 views
Payoff matrix of a scenario and the Schelling point.
Consider the problem of two people trying to drive safely on a two lane road. Each player can drive on their right or left. If players follow the same convention, they’ll drive safely. If they do not, ...
0
votes
1answer
267 views
Convert sentence into First order predicate logic.
a) rabin likes only CSit Course
b)science course are hard.
c)all courses in CSIT are easy
d)CSC 101 is a csit course.
4
votes
2answers
119 views
Regarding Research in Artificial Intelligence [closed]
Which mathematical areas are important for research purposes in artificial intelligence? Specifically, If I have Masters in Statistics how much it will be beneficial for research in artificial ...
3
votes
1answer
60 views
Optimizing a function through reinforcement learning.
I want to know if reinforcement learning can be used for such optimization problems:
\begin{align}
& \max_{p_1^t, p_2^t}\quad\log_2(1+ p_1^t h_1^t)+\log_2(1+ p_2^t h_2^t) \\[6pt]
\text{s.t. } &...
15
votes
4answers
585 views
What areas of math can be tackled by artificial intelligence?
Artificial intelligence is nearing, with image/speech recognition, chess/go engines etc. My question is, what areas of math that are interesting to mathematicians, is likely to be the first to be able ...
0
votes
1answer
170 views
How to First order logic procedure convert Convert to Conjunctive Normal Form ?
How to below this First order logic procedure convert Convert them into Conjunctive Normal Form ?
Ɐx [[employee(x) ꓥ ¬[PST(x) ꓦ PWO(x)]] → work(x)]
I strive to do this below step ,
i. S1: ...
-1
votes
2answers
86 views
How to write the below paragraph in First Order Logic and Convert them into Conjunctive Normal Form
I tried to do this. but this is uncertain. see this below my answer. Please kindly help for me. how do you do this.
Any employee who does not participates for the strike or work in
contract basis ...
1
vote
0answers
46 views
Bayesian Network Probability
Question # 1: On the network which I posted above, I am having trouble determining what the probability of:
P(A,F)
is and how it is derived?
My thinking was that if you have this event (A) that is ...
1
vote
1answer
40 views
Minimize the maximum value returned by paths of an oriented graph in a minimum of transformations
I'm definitely not a math expert so please forgive me in advance for not using the proper vocabulary or conventions. I'm kind of stuck with the following situation in a project of mine:
I have been ...
1
vote
0answers
56 views
Understanding the definition of general knowledge between agents
Background
Consider a set of possible states, $W$. An agent, $i$ has knowledge of a fact $E\subseteq W$, $K_iE=\{w|\sim_i[w]\subseteq E\}$, where $w\in W$ and $\sim_i[w]=\{w'|(w, w')\in\sim_i\}$ is ...
1
vote
1answer
353 views
Find boolean function without brute force truth table?
I have the following homework (AI-related):
Which boolean function does the following TLU (threshold logic unit) implement? The TLU (threshold logic unit) has five inputs. Its weight vector is (1.1, 3....
0
votes
1answer
139 views
Grounded vs. Preferred Semantics (Dung) [closed]
How does Dung's Grounded Semantics framework work in practice? I got this from slides of an AI course but can't figure it out:
Grounded Semantics is said to minimize amount of arguments IN (green) ...
0
votes
0answers
13 views
In Dempster-Shafer theory, is it possible for a BPA to be equal to 0(zero) or 1?
Can a Basic probability assignment for an event A, m(A)=1 or 0.
m(A) could be a decision output for any classifier.
1
vote
0answers
25 views
Clustered Regions by Each Neuron in Self Organizing Map (SOM)
I was given a question about SOM.
There is a SOM which have 4x4 neurons and each neuron's x1 and x2 values (coordinates) given. Also neighborhood function and weight update rule given. How can i find ...
0
votes
1answer
253 views
How to find the conditional independence?
I reviewing some AI books and recently i found the following question that i would like to solve:
In the given Bayes network, decide the conditional independence of the nodes.
Justify ...
1
vote
1answer
50 views
Bayesian network
I have this following question and i would like to know if anyone can answer it.
For a given Bayesian network where $P(a) =.6, P(b|a) =.8, P(b|-a)=.4, P(c|a)=.4$ and $P(c|-a) = .3$, compute $P(c|b)$. ...
0
votes
1answer
36 views
Weird logarithm rules in an attempt to proof an upper bound of JSD between two Gaussian distribution
I'm currently working on my thesis in Deep Learning and stumbled upon one paper that I think is really related to my topic. In short, I could not understand some parts of its computation process. Here'...
0
votes
1answer
431 views
How to prove this using resolution theorem or resolution refutation?
I need to prove P v (Q ^ R), S : (S ^ P) v Q using resolution theorem or resolution refutation. This is my proof:
Convert P v (Q ^ R) to (P v Q) ^ (P ^ R)
Convert ...
0
votes
2answers
57 views
De morgan quantifers prove
prove ∃x (P(x) => Q(x)) = ∀x P(x) => ∃x Q(x)
∃x (P(x) => Q(x))
= ∃x (¬P(x) ∨ Q(x)) ----- (1)
= ∃x(¬P(x)) ∨ ∃xQ(x) ----- (2)
= ¬∀xP(x) ∨ ∃xQ(x) ----- (3)
= ∀x P(x) => ∃x Q(x) ----- (4)
From line ...
