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
Join us in building a kind, collaborative learning community via our updated Code of Conduct.

For questions about implementing and improving optimization algorithms used in creating AI programs, or optimization in general.

2
votes
1answer
23 views

Genetic Algorithms: Trade-off between time and variance with regards to fitness function

I'm developing an AI to play a card game with a genetic algorithm. Initially, I will evaluate it against a player that plays randomly, so there will naturally be a lot of variance in the results. I ...
1
vote
1answer
21 views

How do I compute log-likelihood for training set in supervised learning?

I am building a supervised learning model and I wish to compute the log-likelihood for the training set at the point of the minimum validation error. Initially, I was computing the sum of all the ...
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 ...
1
vote
1answer
23 views

Quiescence search

Games like checkers have compulsory moves. In checkers for instance, if there's a jump available a player must take it over any non-jumping move. My question is, if jumps are compulsory will there ...
3
votes
2answers
29 views

Is an evaluation function as good as an optimization function

I have been so for self-learning basic A.I concepts and would like to know if having a really good evaluation function as good as any of alpha-beta pruning optimization functions such as killer moves, ...
2
votes
0answers
21 views

Gradient of boltzmann policy over reward function

I'm struggling with an inverse reinforcement learning problem which seems to appear quite often around the literature, yet I can't find any resources explaining it. The problem is that of calculating ...
0
votes
0answers
40 views

reinforcement learning rmsprop does not improve, average reward through time oscillates

I have a reinforcement learning project using policy gradient method with rmsprop optimization. (used vanilla REINFORCE algorithm)(the game is a simple pong game in open-ai gym atari environment) the ...
2
votes
1answer
92 views

If Deep Learning is non convex, then why use convex loss?

I was just reading through some convex optimization textbooks to hopefully improve my deep learning understanding and come up with new ideas. Halfway through, I decided to Google a bit! It's obvious ...
0
votes
1answer
26 views

Can TensorFlow minimize “symbolically”

From https://stackoverflow.com/questions/36370129/does-tensorflow-use-automatic-or-symbolic-gradients, I understood TensorFlow requires all the operations in the Graph to be explicit formulas (instead ...
2
votes
2answers
58 views

Input optimization on a supervised learning system

Problem Given a collection of pairs (X, y) where X belongs to R^n and y belongs to R, find the X such that the associated y would be maximum. Example Given: (X=(1, 2), y=-9) (X=(-2, 4), y=-36) (X=...
6
votes
1answer
100 views

Why does a one-layer hidden network get more robust to poor initialization with growing number of hidden neurons?

In a nutshell: I want to understand why a one hidden layer neural network converges to a good minimum more reliably when a larger number of hidden neurons is used. Below a more detailed explanation of ...
3
votes
1answer
24 views

How to use MOPSO to align characters vertically?

I need to efficiently align characters vertically using Multi Objective PSO. Alignment is achieved by adding spaces in between a given set of characters. ...
6
votes
2answers
817 views

Time complexity for training a Neural Network

So, I was wondering: what is the time complexity of NN? Say we take the simple case of the back-propagation algorithm with n hidden layers, ...
4
votes
1answer
116 views

Why number of hidden units in a layer are suggested to be in powers of 2?

It is suggested that the number of hidden units in a layer should be in powers of 2 because it helps converge faster. Is it a fact and if it is, how this helps the NN learn faster. Does it have to do ...
1
vote
0answers
28 views

How to calculate Adaptive gradient?

In the FaceNet paper there mentions an gradient algorithm called 'AdaGrad'(Adaptive Gradient) referenced to this paper which has apparently been used to calculate the gradient of the Triplet Loss ...
1
vote
0answers
67 views

Application of Ai to task scheduling problems on heterogenous platforms

Let's say we have a cluster of 20-2000 heterogenous compute nodes. Consider for example the parallel solution of the helmholtz equation: Now we want to distribute the solution process and, to make ...
0
votes
1answer
27 views

Should the mutation be applied with the hill climbing algorithm

As far as I understand, the hill climbing algorithm is a local search algorithm that selects any random solution as an initial solution to start the search. Then, should we apply an operation (i.e., ...
2
votes
0answers
67 views

Which features and algorithm could optimize this air-conditioner problem?

Imagine we have 2 air conditioner systems (AA) and 2 "free cooling" systems which mix external and internal air (FC) in a closed box which always tends to warm up. For each system, we have to find ...
1
vote
0answers
26 views

Which algorithm would you use to solve a multiple producer-consumer problem with constraints?

I'm solving this problem similar to consumer-producer of materials (i.e. sand). This is the graph of the problem: Where Req (...
7
votes
1answer
89 views

Why does 'loss' change depending on the number of epochs chosen?

I am using Keras to train different NN. I would like to know why if I increment the epochs in 1, the result until the new epoch is not the same. I am using shuffle=False, and np.random.seed(2017), and ...
7
votes
1answer
513 views

Why is the merged neural network of Alpha Go Zero more efficient than two separate neural networks?

Alpha Go Zero contains several improvements compared to its predecessors. Architectural details of Alpha Go Zero can be seen in this cheat sheet. One of those improvements is using a single neural ...
2
votes
0answers
65 views

Problems getting ADADELTA to converge

I have followed the pseudocode in the ADADELTA paper (top right on page 3), and wrote the following Python code for solving the optimization problem L(x) = x^2: ...
6
votes
1answer
1k views

What is the difference between Memetic Algorithms and Genetic Algorithms?

Can someone please explain the difference between Memetic Algorithms and Genetic Algorithms? Is an indivudal's lifetime learning part of memetic algorithms?
2
votes
0answers
59 views

Reproduce Firefly Algorithm experiments of original paper?

I have been trying to reproduce the experiments done in the original: "Firefly Algorithm for multimodal optimization" (linked in the question) so far: unsuccesfully. For the moment being I'm okay if ...
2
votes
0answers
28 views

Knapsack of mixture with constraints

I'm trying to find the optimized mixture for a specific set of substances. Each of those substances have characteristics that I want to optimize in the mixture (some characteristics I want to minimize ...
1
vote
1answer
64 views

How to find proper parameter settings for a given optimization algorithm?

Is there any methodology to find proper parameter settings for a given meta-heuristic algorithm, eg. Firefly Algorithm or Cuckoo Search? Is this an open issue in optimization? Is extensive ...
1
vote
1answer
531 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 ...
7
votes
1answer
300 views

What are Hyper-heuristics?

I wanted to know what the differences between hyper-heuristics and meta-heuristics are, and what their main applications are. Which problems are suited to be solved by Hyper-heuristics?
2
votes
2answers
48 views

Is there a way to define the boundaries of the optimal size of a training set?

At a related question in Computer Science SE, a user told: Neural networks typically require a large training set. Is there a way to define the boundaries of the "optimal" size of a training set ...
9
votes
2answers
172 views

Can artificial intelligence be thought of as optimization?

In this video an expert says, "One way of thinking about what intelligence is [specifically with regard to artificial intelligence], is as an optimization process." Can intelligence always be thought ...
2
votes
1answer
59 views

What are the methods of optimizing overfitted models?

I'm worrying that my network has become too complex. I don't want to end up with half of the network doing nothing but just take up space and resources. So, what are the techniques for detecting and ...