Questions tagged [artificial-intelligence]

Questions about design and properties of agents that act in a dynamic environment and make decisions towards some goal without user control.

Filter by
Sorted by
Tagged with
2
votes
1answer
448 views

What does the posterior probability of a variable mean in the Bayes' rule?

I have been studying Artificial Intelligence and I have noticed that the Bayes' rule allows us to infer the posterior probability if a variable. But, my question is, what does the word, or phrase, '...
2
votes
2answers
3k views

iterative lengthening search example

I am looking for an example of the "iterative lengthening search". I have searched and I was only able to find definitions like iterative lengthening search an iterative analog to uniform cost ...
2
votes
1answer
955 views

How to recognize a STRIPS planning problem has no solution?

Strips –Stands for STanford Research Institute Problem Solver (1971). STRIPS Pseudo code - ...
2
votes
1answer
41 views

How would one construct conjunctively local predicate of order k for checking if a shape is Convex?

I was reading Minsky's and Papert's book on perceptrons and it had the definition of conjunctively local as follow (look at the last images if its still unclear): A predicate $\psi$ is conjunctively ...
2
votes
1answer
201 views

Why do we use the log in gradient-based reinforcement algorithms?

I've been reading some papers on reinforcement learning. $$\Delta w=\frac{\partial ln\ p_w}{\partial w}r$$ I often see expressions, similar to the above one, where the weights (denoted by $w$) are ...
2
votes
1answer
34 views

Can high-order unification be applied to programming by example?

In 2007, it has been proven that high-order unification is decidable on the pattern matching case. If that is true, what is stopping someone to write an equation like: ...
2
votes
1answer
395 views

What kind of Neural Network (if any) could fit two sets of data points?

I have two datasets, one of animal migration patterns (collected over the course of a couple years) that consists of many points on an x, y plane (latitude, longitude), and the other of ocean surface ...
2
votes
1answer
492 views

Can the effective branching factor be negative?

I've implemented A* algorithm in Python, after that I calculated the effective branching factor $ B^* $ $$ T+1=1+B^*+(B^*)^2+\dots +(B^*)^L$$ where $T$ is the number of expanded nodes. My question ...
2
votes
2answers
253 views

Guessing the best choice to maximize returns

There are $N$ number of people and $X$ amount of objects with different values. Each person will choose an object and will obtain that objects value. If multiple people choose the same object then the ...
2
votes
2answers
12k views

Nim game tree + minimax

Problem : Two players have in front of them a single pile of objects, say a stack of 7 pennies. The first player divides the original stack into two stacks that must be unequal. Each player ...
2
votes
1answer
7k views

Example using Penetrance & Branching Factor in State-space Heuristic Search

I need an example for how to calculate penetrance and branching factor of the search tree in in state-space heuristic search. The definitions are as following. Penetrance $P$ is defined by $\qquad \...
2
votes
1answer
37 views

Decision Tree Learning Deviation - Russell and Norvig

I am working through the Russell and Norvig AI book and came across the following on the top of page 706. The section concerns Decision Tree pruning and testing a given attribute against the null ...
2
votes
1answer
333 views

What can't be done with a neural network

This reference from the german wikipedia article on neural networks states: There are also many other important problems that are so difficult that a neural network will be unable to learn them ...
2
votes
1answer
963 views

Beam size is a parameter in some RNNs like TensorFlow's Magenta. What is beam size?

Magenta's melody_rnn_generate method includes a parameter beam_size. What is it and how does affect the melody?
2
votes
1answer
184 views

In Lbest PSO, how is the local best position in a neighbourhood defined?

I am implementing a couple of PSO (particle swarm optimization) algorithms, and I got stuck on a bit of detail which I could not clearly determine from the papers I have read. In lbest PSO, for each ...
2
votes
1answer
46 views

How to model a set of categorical values in the input of a neural network

One of the inputs to my neural network is a set. I have a set $S = \{s_0, s_1, ..., s_n\}$ in which all values $s_i$ are constant. An example of such a set could be the set of French wines (...
2
votes
1answer
72 views

What Exactly is “Improvement” in Seed AI?

From LessWrongWiki, a seed AI [I]mproves itself by recursively rewriting its own source code without human intervention. Some would even say this could bring about an Intelligence Explosion. Many ...
2
votes
1answer
597 views

Role of computational power in recent AI developments

Today Google's AI won its first game of Go against Lee Sedol, one of the best Go players on the planet. Image interpretation and self-driving cars are other recent success stories in machine learning. ...
2
votes
1answer
86 views

What is a good example to illustrate the difference between isomorphic and homomorphic representations?

I am learning about "knowledge representation" in my intro to AI course and one of the key ideas has to do with isomorphic vs homomorphic representations. The examples I find when I google around are ...
2
votes
1answer
713 views

Difference between heuristic-based searching and optimal path searching

I'm currently studying for an AI computer-science course. One thing is difficult for me to grasp and somewhat vaguely explained in my course-material: I understand that with search-methods like e.g. ...
2
votes
1answer
368 views

Perceptron learning rule past exam question

I'm struggling to solve this past paper question and my lecturer is being less than helpful. The question is: Apply the perceptron learning rule to update the current weight vector (0.1, 0.3) when ...
2
votes
1answer
976 views

Differences between linear/nonlinear vs. deterministic/nondeterministic neural nets

When speaking of neural networks, I don't get the difference between nonlinear and non-deterministic. Basically, both say that the output of something is not directly correlated to the input? Hope ...
2
votes
1answer
1k views

Artificial intelligence - bridge and torch problem

I am doing a artificial intelligence course as part of my computer science degree. I am stuck on a question about searching. The question is a version of the Bridge and torch problem. Five people ...
2
votes
1answer
596 views

first order logic resolution unification

Assuming I have shown part of the knowledge base in the clausal format: [1] p1(banana). [2] not p1(X) or p2(Y). [3] p1(X) or not p3(F). ... and more rules. ...
2
votes
1answer
78 views

Does domination rule apply for inadmissible heuristics?

Let's say $h_1(n) \geq h_2(n)$ so that dominance is established even if $h_1$ and $h_2$ are both inadmissible/non-optimal heuristics -in whichever given search space. Is $h_1$ still faster/better ...
2
votes
1answer
95 views

Proving Monotonicity of Softmax Layer

In the book here: http://neuralnetworksanddeeplearning.com/chap3.html If you scroll down to Exercise 2 in the Softmax Section, it says Show that $\partial a^L_{j}/\partial z^L_{k}$ is positive if $...
2
votes
1answer
51 views

Understanding Alpha Beta Pruning: Why do we ignore the values of a unsearched tree after the first leaf, can they not include acceptable values too?

So this is my question. I am trying to understand this part of the book: At d) why do we stop looking at the other nodes in that branch? There could be a acceptable value next to the 2? I am just ...
2
votes
1answer
46 views

The task of recognizing game units in the screenshot

I'm new to computer vision and I want to solve the task of recognizing the game units of the game Clash Royale in the screenshot. Briefly, there are about 70 different types of gaming units belonging ...
2
votes
2answers
1k views

What kind of pattern recognition algorithm would Facebook use to detect suicidal users?

Facebook announced that it would employ a machine learning "reporting process using pattern recognition in posts previously reported for suicide" (https://newsroom.fb.com/news/2017/03/building-a-safer-...
2
votes
1answer
72 views

What determines the number of inputs and outputs when initialising weights in a convolutional neural network?

Following Deep MNIST for Experts tutorial on Tensorflow, I realize I don't understand where the choice of numbers comes from when initializing weights. In the tutorial, they first show the below ...
2
votes
1answer
30 views

how to approximate a very complex optimal policy when the distance function is unknown

A policy $P$ is defined as a set of parameters. We want to know the optimal policy $O$, which certainly exists but unfortunately unknown. $D(P)$ shows how far $P$ is from $O$. The function $D$ itself ...
2
votes
1answer
716 views

Semantic natural language processing - from texts to logical expressions? Universal knowledge base?

My question is - is there a semantic natural language processing that tries to understand the meaning of the texts and that tries to derive the consequences of the understood meaning? Is there a ...
2
votes
1answer
269 views

Convergence of Markov model

I was learning Hidden Markov model, and encountered this theory about convergence of Markov model. For example, consider a weather model, where on a first-day probability of weather being sunny was 0....
2
votes
1answer
402 views

decidability of artificial intelligence

Not sure whether this is the correct place to post the question. some of my terms might not accurate. currently AI is used for classification, inference, and so forth, is AI problem decidable? for ...
2
votes
1answer
844 views

Understanding the Broyden–Fletcher–Goldfarb–Shanno Algorithm to Select Weights for Neural Nets

I am trying to train and implement a Neural Network. I was reading a few articles, learning about their principles and the math that goes behind them. However, while I was trying to understand the ...
2
votes
1answer
134 views

Reinforcement Learning - Q Learning

I am having trouble understanding the following problem and Q learning in general. What I know so far about Q learning is that Q-learning is a model free method, i.e., it doesn’t need to learn P(s’|...
2
votes
2answers
70 views

How should i guide a program to perform correct things? [closed]

I want to make a small model of A.I. which can learn itself. I am inspired by 1000+ monkey theorem which states that if 1000+ monkey bangs a keyboard for enough long, then they will eventually produce ...
2
votes
1answer
194 views

How do I stop “cheating” in reinforcement learning (MLP+Evo. Algorithm)?

I have a two hidden-layer MLP. I am trying to teach it classification of the sine function. For instance, if there is an [x,y] point above the sine function, the ANN should classify that point as a 1. ...
2
votes
1answer
132 views

Why Isn't This Outlier Score/Reconstruction Error Not Squared?

I was looking through a paper called "AI2 : Training a big data machine to defend", and saw this (http://people.csail.mit.edu/kalyan/AI2_Paper.pdf) $score(X_{i}) = \sum_{j=1}^{p} (|X_{i} − R^{j}_{i}|)...
2
votes
1answer
101 views

Robot lawyer algorithm [closed]

I have a background in physics and have taken some few classes online in Machine learning. But I really do not understand how this Robot lawyer can work: A 19-year-old made a free robot lawyer that ...
2
votes
1answer
2k views

Table-Driven Agent Program

I have two questions regarding a paragraph about table-driven agent programs from Modern Approach to Artificial Intelligence 3rd Edition. "Let $\mathbb{P}$ be the set of possible percepts and let T ...
2
votes
1answer
126 views

How to determine convergence when using Q-learning?

I'm using Q-Learning to find the values of states in on a gameboard. For example, something like: ...
2
votes
1answer
80 views

Updating connections weights in neural networks

I am learning about neural networks and have a couple of things I don't understand. Firstly, in competitive learning I understand that only the neuron with the strongest output is reinforced. That is ...
2
votes
1answer
38 views

basic doubt on policy iteration

consider the policy iteration algorithm for a finite state MDP. Suppose the initial policy is a stochastic policy. Now, can the optimal policy be deterministic after improvements ? Or, can we say that ...
2
votes
3answers
2k views

Rational agent question from Russell and Norvig

Question from Artificial Intelligenge: A Modern Approach by Russell and Norvig (Exercise 2.1). Suppose that the performance measure is concerned with just the first $T$ time steps of the ...
2
votes
1answer
429 views

What is the purpose of Bayesian networks?

I have seen a lot of explanations of what Bayesian networks are, but I simply cannot wrap my head around their use in code. So here is my three part question. Am I right in my definition of Bayes ...
2
votes
0answers
17 views

How are image processing and computer vision related to artificial intelligence.?

We have often heard both terms image processing and computer vision in AI sessions But i am confused, how they both are related to artificial intelligence?
2
votes
0answers
18 views

Why aren’t (type theory based) automated theorem provers efficient?

Note: my main experience with theorem provers is with Type theory based proof-assistant, rather than an actual automated theorem prover. It is obvious why naive automated theorem proving is ...
2
votes
0answers
43 views

Literature similar to Minsky's “Steps Toward Artificial Intelligence” (1961)?

With great pleasure I was just reviewing Marvin Minsky's publication "Steps Toward Artificial Intelligence" from 1961. Now I would like to know whether there are any more compilations about the ...
2
votes
0answers
51 views

Is one of the Advantages of AI symbolic systems the fact they are good at abstraction and modularity according to Minsky and Papert?

I was reading Perceptron's by Minsky's and Papert's book and there is a part where they discuss symbolic systems and one part of it says: Symbolic systems yield gains of their own...Above all else ...