Stack Exchange Network

Stack Exchange network consists of 174 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [math]

For questions about mathematics related to artificial intelligence.

1
vote
1answer
50 views

Reward-related formulation in reinforcement learning

I am referring to eq. 3.6 (p/g 49) based on Sutton's online book and can be found in an image below. I could not make sense of the final derivation of the equation $r(s, a, s')$. My question is ...
5
votes
3answers
86 views

Applied Math relevant to AI

My background is in electrical engineering (BS, MS EE/Signal Processing) and I have a good grasp of CS foundations (Data Structures, Algorithms, OS, Discrete Math) and software engineering. I have ...
3
votes
2answers
149 views

Is known math really enough for AI

As an Electronics & Communication Engineering student I've heard some stories and theories about "The math we have is not enough to complete a thinker-learner AI." What is the truth? Is humankind ...
1
vote
1answer
28 views

Weight Normalization paper

I am trying to dissect paper about weight normalization: https://papers.nips.cc/paper/6114-weight-normalization-a-simple-reparameterization-to-accelerate-training-of-deep-neural-networks.pdf ...
4
votes
1answer
69 views

What are the algebraic properties of intelligence?

Some have said, "Two heads are better than one." That's true if they are collaborating. If not, the two together may be worse than zero. Although that's a rhetorical opening paragraph, this is a ...
3
votes
2answers
371 views

Why is the derivative 0 if the policy is deterministic?

In the Berkeley RL class they mention the gradient would be 0 if the policy is deterministic. Why is that? https://www.youtube.com/watch?v=XGmd3wcyDg8&feature=youtu.be&t=1071
5
votes
1answer
58 views

What makes multi-layer neural networks be able to perform nonlinear operations?

As I know, a single layer neural network can only do linear operations, but multilayered ones can. Alao I recently learned that finite matrices/tensors, which are used in many neural networks can ...
3
votes
2answers
68 views

Are there any discount-factors based on branching factors?

I recently came across this function: $$\sum_{t = 0}^{\infty} \gamma^t R_t.$$ It's elegant and looks to be useful in the type of deterministic, perfect-information, finite models I'm working with. ...
1
vote
0answers
24 views

Optimization step in Apprenticeship Learning via Inverse Reinforcement Learning

Why the optimization step of the algorithm a quadratic program? [See: Apprenticeship Learning via Inverse Reinforcement Learning; page 3] Isn't the objective function linear? Why don't we treat ...
10
votes
4answers
410 views

Can deep networks be trained to prove theorems?

Assume we have a large number of proofs in first order predicate calculus. Assume we also have the axioms, corollaries, and theorems in that area of mathematics in that form too. Consider the each ...
7
votes
3answers
170 views

Mathematics for AI researcher

What are the mathematical prerequisites for understanding the core part of the algorithms in artificial intelligence and developing own algorithm? Please refer me the specific books.
3
votes
1answer
90 views

Mathematical modelling of A.I algorithms

How does one even begin to mathematically model an A.I algorithm like alpha-beta pruning or even its thousands of variations, to determine which variation is best?
1
vote
0answers
20 views

Simple question about HS algorithm's formul(Optical flow)

In the below pic, I can not understand what U vector is? It says flow field but I can not imagie what really is the flow field?
1
vote
0answers
66 views

How does this sigma work?(Harris algorithm) [closed]

May someone explains some first iterations of this sigma? Also, how did it convert the above expression to below expression? What it the meaning of I(x) and I(y)?
10
votes
2answers
188 views

Is there any scientific/mathematical argument that prevents deep learning from ever producing strong AI?

I read Judea Pearl's The Book of Why, in which he mentions that deep learning is just a glorified curve fitting technology, and will not be able to produce human-like intelligence. From his book ...
2
votes
1answer
59 views

Defining formula for fuzzy equation

I'm learning fuzzy logic and more or less understand the basic concept, but i'm having a hard time understanding how to apply it to a method. I tried browsing online for explanation on how to use it, ...
0
votes
0answers
38 views

Back propagation in NN with sigmoid activation function - division by 0

I am following this article Mind: How to Build a Neural Network (Part One) to build 'hello world' in the world of neural networks - XOR. During the back-propagation phase author calculates changes in ...
2
votes
5answers
1k views

What maths are required to study General AI?

I want to know what maths prerequisite is needed for moving deep in general Artificial Intelligence or strong AI
2
votes
0answers
160 views

How to calculate gradient of filter in convolution network

I have similar architecture like in image:CNN. I don't understand how to calculate gradient of filter F. I found these equations(source): Gradient and delta, where first equation calculate gradient ...
2
votes
3answers
75 views

Cost Function Question

I have completed week 1 of Andrew Ngs course and I understand that the cost function for linear regression is defined as J (theta0,theta1) = 1/2m*sum (h(x)-y)^2 and the h is defined as h(x) = theta0 + ...
1
vote
1answer
41 views

Please explain this “log probability function”? What does each part mean?

Can anyone explain what information the formula gives us. What does the notations mean? Where i can find more material about what does the log probability function do?
3
votes
1answer
75 views

K-Armed Bandit and Reinforcement Learning

In the book "Reinforcement learning" by Sutton there is a discussion of the k-armed bandit problem, where the expected reward from the bandits changes slightly over time (is non-stationary). Instead ...
3
votes
2answers
226 views

Viola Jones Algorithm

Can Viola Jones algorithm can be used to detect the facial emotion. Actually it was used in creating harr-cascade file for object and facial detection. But what confused me is whether it can be used ...
3
votes
5answers
417 views

Artificial Intelligence and its mathematics

I would like to ask community members what kind of knowledge is required to jump into the field of AI. Currently I have just started programming and development. What should I pursue in order to get ...
7
votes
6answers
759 views

Getting started with Artificial intelligence

I'm currently pursuing Computer science engineering.So I would like to know where to start and what mathematics is needed to jump in.
7
votes
6answers
10k views

How does one start learning artificial intelligence?

I am a software engineering student and I am complete beginner to AI. I have read a lot of articles on how to start but each article suggests a different way. I was wondering if some of you experts ...
2
votes
1answer
45 views

Why expression of cost function divides by 2? [closed]

Here is formula for calculating cost value of single neuron: C_x = (1/2) * || y - a ||^2 why there is 1/2?
2
votes
1answer
619 views

Are FFNN (MLP) Lipschitz functions?

My question is regarding standard dense-connected feed forward neural networks with sigmoidal activation. I am studying Bayesian Optimization for hyper-parameter selection for neural networks. There ...
5
votes
1answer
164 views

Is recursion used in practice to improve performance of AI systems?

Is there any methods by which artificial intelligence use recursion(s) to solve a certain issue or to keep up working and calculating?
-6
votes
2answers
181 views

What are the approaches to predict sequence of π numbers? [closed]

Given list of fixed numbers from a mathematical constant such as Pi, is it is possible to train AI to attempt to predict the next numbers? Which AI or neural network would be more suitable for this ...
14
votes
4answers
7k views

Is it possible to train the neural network to solve math equations?

I'm aware that neural networks are probably not designed to do that, however asking hypothetically, is it possible to train the deep neural network (or similar) to solve math equations? So given the ...