Questions tagged [machine-learning]

Questions about computer algorithms that automatically discover patterns in data and make good decisions based on them.

Filter by
Sorted by
Tagged with
0
votes
0answers
19 views

How does neural net complexity relate to other complexity measures?

In neural networks, "weight regularization" is often used as a so called "complexity penalty" in order to make sure that the network generalizes better from training data. Similarly, in "program ...
0
votes
0answers
85 views

What is the relationship between pairwise loss and centroid loss?

What is the relationship between pairwise loss and centroid loss? Under what conditions you would expect them to give similar behavior? Under what conditions would they give different behavior?
1
vote
0answers
15 views

How to compute the sample update error?

In the book Reinforcement Learning An Introduction,Chapter 8.5,there is an example that compares the efficiency of expected and sample updates: According to the author, "In this case, sample updates ...
0
votes
0answers
10 views

OR functions and SQ-Learning

Anyone can describe or give a reference which has a clear description and detailed proof of the SQ-Learning algorithm for the OR class of Boolean functions?
-1
votes
1answer
34 views

How can I represent the following mathematically? (Eigenfaces reconstrcution)

I got the following from a web site: The feature vectors represent each image as a linear combination of the eigenfaces defined by the coefficients in the feature vector; if we multiply each ...
2
votes
0answers
47 views

Card dealing problem with constraints (blacklisting),

A friend of mine and I are trying to teach a bot play a card game (bela) We are using monte carlo tree search (MCTS) to estimate the probability of winning hand in regards to multiple possible (!...
1
vote
1answer
98 views

(OCR ) How to Recognise Handwritten fractional numbers using Neural networks

I want to be able to recognise handwritten math numbers using images of the numbers , i was able to do create a ANN model for recognising simple decimal numbers , but i have no idea on how to ...
1
vote
1answer
120 views

Help needed for understanding proof of No Regret Multi Armed Bandit Algorithm

I was reading Elad Hazan's book on Online Convex Optimization(http://ocobook.cs.princeton.edu/OCObook.pdf) and am facing difficulty understanding the proof given for the No regret algorithm for MAB (...
1
vote
1answer
63 views

Do data points mean Eigenfaces in higher dimensional space?

I saw the following animation at making sense of PCA , which shows blue data points. I am reading a paper on Eigenfaces which says that: "a typical image of size 256 by 256 becomes a vector of ...
1
vote
0answers
53 views

Machine learning for VLSI floorplanning tool

I have an educational assignment to make an VLSI floor-planning tool. Can I use machine learning in some part of the algorithm? For example, I was reading the book Algorithms for VLSI Physical Design ...
0
votes
1answer
134 views

What is the difference in SMO algorithm for SVM and SMO for one class?

Please let know if this is not the correct forum to ask this question. If not can anyone please tell where can I ask this question? I am trying to understand the difference between the paper : https:/...
1
vote
1answer
35 views

Problem with Understanding “correlated attributes into a set of values of uncorrelated attributes” in PCA

I am studying PCA. I have a problem in understanding the following concept: What is meant by transforming "correlated attributes into a set of values of uncorrelated attributes" in Principal ...
1
vote
0answers
28 views

Is there an equivalent of “control flow” in deep learning systems?

Traditional programs work significantly through control flow. I know that there are simple algorithms that have no control flow at all (i.e. they just perform a fixed sequence of executions), but I ...
0
votes
0answers
9 views

Looking for a specific type of ADMM iterates

For a $k-$dimensional optimization variable $b \in \mathbb{R}^k$ say the objective is given as, $$f(b) = \langle b, v \rangle + \langle b , Ab \rangle + \lambda \Vert b \Vert_1$$ for some parameter ...
1
vote
1answer
72 views

Show that the Laplace smoothing for bigrams is a valid probability distribution

If we consider any smoothing technique like laplace or delta smoothing. Intuitively we can see that the we are stealing from sequences with non zero probablity and re distribute to sequences with zero ...
1
vote
0answers
108 views

Proof of perceptron convergence theorem for ZERO threshold?

The generalized perceptron convergence theorem is for a defined threshold T. When you do the maths it all comes to an upper bound and a lower bound. The lower bound looks like this! Therefore ...
1
vote
1answer
42 views

Checking if a kernel is valid

The kernel is $K(x,z) = \sum_{i=1}^D (x_i+z_i)$ My approach was trying to express $K = \phi(x)^T\phi(z) = (x_1 x_2 ... x_D \quad 1 1 ...1)(1 1 ...1\quad z_1 z_2 ... z_D )^T$ where $\phi$ is 2Dx1 ...
2
votes
1answer
44 views

Is Artificial General Intelligence possible with our current machine learning models? [closed]

In other words, is artificial human level intelligence not possible yet just because of limitations in processing power and amount of data required to train the models? Or we don't have the knowledge ...
0
votes
0answers
14 views

Applications of signed permutations to machine learning

Are there some applications of signed permutations to machine learning? I searched on google and only found one paper. Thank you very much.
1
vote
1answer
37 views

Matching/finding mathematical plot images

I'm trying to come up with a method to match a given mathematical plot against a database of other plots. To make it more specific: plots are generated in R as PNG and might have different dimensions. ...
3
votes
1answer
26 views

Why doesn't this derivation of the margin in a SVM give the correct result?

I'm trying to derive the optimization objective for an SVM (namely $1/\|w\|$), but I'm running into a little trouble. I've already read this question, which has certainly offered a lot of insight into ...
1
vote
1answer
38 views

The notion of PAC in approximation algorithms

In computational machine learning, the notion of Probably Approximately Correct means that (generally speaking) we can find (or "learn") with a high probability a function which has "low error". Is ...
0
votes
1answer
22 views

Choose the best classifier to predict the label of strings of a regular language

I have to tackle this problem: I have some strings that are my training set. These strings belong to a regular language corresponding to a deterministic finite automata (hidden namely I don't now it, ...
2
votes
1answer
400 views

Mathematical proof for why gradient descent algorithm always converges

I am currently learning machine learning and I stumbled across gradient descent. I understand why the algorithm always converges to the global/local minimum when the learning rate is small enough in ...
1
vote
0answers
37 views

What are good examples of computational theories for A.I. according to David Marr's Definition?

I was reading David Marr's "Artificial Intelligence-A Personal View" and he talks about "computational theory of AI" or what he laters labels as "Type 1" Theory. He provides the example of Chomsky's ...
-3
votes
2answers
393 views

Does deep learning infer P = NP?

The question comes from the following scenario, assume we have the traveler problem which is NP (the one where a traveler wants to visit all countries with the lowest cost(by summing up all flights)) ...
1
vote
3answers
1k views

What is the “spatial information” in convolutional neural network

deep learning research papers always claim that deeper layers of CNN have good "semantic information" but poor "spatial information". What is the spatial information exactly. Is that some activations ...
3
votes
0answers
32 views

How to compute the loss and backprop of word2vec skip-gram using hierarchical softmax?

So we are calculating the loss $$J(\theta) = -\frac{1}{T}\sum_{t=1}^T\sum_{-m \leq j \leq m} \log P(w_{t+j}|w_t;\theta)$$ and to do this we need to calculate $$P(o|c) = \frac{\exp(u_o^Tv_c)}{\sum \...
1
vote
1answer
211 views

VC dimension of finite unions of one-sided intervals

What is the VC dimension of $k$ finite unions of one-sided intervals: If we take 3 one-sided intervals like $(-\infty, a_1] $, $(-\infty, a_2] $ and $(-\infty, a_3] $, I think union of these ...
1
vote
1answer
93 views

Cost of computational representation in PAC-learning definition

I'm currently reading Foundations of Machine Learning by M. Mohri, A. Rostamizadeh, A. Talwalkar and according to their definition a concept class $C$ is said to be PAC-learnable if $$Pr_{S \sim D^m}[...
1
vote
0answers
27 views

How to get old top news? [closed]

I am not sure this is the right forum to ask. For a machine learning training, I need a dataset of old top news by keywords that can be organized by date. From where I can download it? I have seen ...
3
votes
1answer
51 views

(DROP) Data Reduction Algorithm - How it works?

I am studing a PHD framework which the propose is to reduce the dataset with the most representative samples for training a classifier. Maybe I am loosing something, but I could not undestand a ...
3
votes
1answer
110 views

Weird behaviour of softmax derivative?

I have been implementing some neural networks in MATLAB and recently I noticed a weird thing while implementing softmax derivative: Setting the derivative to one, rather than using the actual ...
0
votes
1answer
81 views

How to calculate the weight between neurons in ANN?

I am currently learning Supervised ANN training using Backpropogation and I am stuck in this exercise. I calculated the δA using the equation at the bottom of the screenshot, however, I am unable to ...
5
votes
2answers
123 views

Why do AlphaGo and AlphaGo Zero include board history in the input features

Both AlphaGo and AlphaGo Zero include prior board states as input features (the "Turns Since" planes for AlphaGo, and the repeated 8-step history planes for AlphaGo Zero). What is the purpose of ...
0
votes
1answer
24 views

Correct cost function of multi classification problem using neural network?

I am going through machine learning course on coursera. While going through the section on neural networks I came across the cost function for multi - classification problem using neural networks ( ...
3
votes
1answer
35 views

Why Don't We Use Non-ML Artificial Evolution?

I remember reading about Tom Ray's Tierra and how amazing the results it obtained were. However as far as I know, the only "evolution" based computer technology we use now is ML, which is very limited ...
0
votes
0answers
50 views

L1 sampling for sampling edges of a graph

I am trying to sample the edges of an undirected graph using weights. The goal is to run a sparsification algorithm on the graph. I see the point that L1 norm is best for sparsification. Can someone ...
3
votes
2answers
78 views

What is the State of The Art of Writer AIs (Deep Learning)?

Does anyone know if Deep Learning Bots can already, for example, train on many books of an author and output a similar but new book? I've been wanting to get into ML for quite a while but was ...
1
vote
1answer
28 views

Identify objects (bus) on the map based on coordinates (lat, lon)

Let's say I have an android app that frequently sends current GPS location of the user. If person is driving with bus, I can easily get GPS location of the bus and display it on the map and update it ...
1
vote
0answers
205 views

How can node2vec help find similar “roles” within a graph (nodes whose connections have similar structure within the graph)?

I have a question on the node2vec algorithm described in this paper. Node2vec is a deep learning algorithm that word2vec to graphs to learn embeddings. The authors claim that it can help find nodes ...
1
vote
0answers
63 views

Why don't Artificial Neural Networks Commonly Diverge?

Introduction: I'm using divergence here as to mean that the gradient is getting further and further from zero in stochastic gradient descent. I've written my own feed-forward neural network and tried ...
2
votes
0answers
81 views

Moon lander algorithm

Not talking about the actual moon lander, but an old game that was inspired by it (see screenshot). Suppose I wanted to write a program that "plays" this game: Can only operate the vertical thruster ...
2
votes
1answer
816 views

Subsampling of Frequent Words in Word2Vec

I am reading through the following paper: https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf Under section 2.3 on page 4 the authors ...
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 ...
1
vote
1answer
75 views

Question on word probability for hierarchical softmax used in natural language processing

I am reading the following paper: https://papers.nips.cc/paper/5021-distributed-representations-of-words-and-phrases-and-their-compositionality.pdf On page 4 of the paper they describe the ...
2
votes
1answer
245 views

Parameter sharing / weight constraints in Neural Networks

I would like to train a neural network whose parameters (alternatively, weights) are subject to linear constraints such as $w_{i,j} = w_{i',j'}$, where $w_{i,j}$ denotes the weight from input node $...
2
votes
1answer
76 views

Is there a universal learning rate for NeuralNetworks?

I'm currently creating a NeuralNetwork with backpropagation/gradient descent. There is this hyperparameter introduced called "learning rate" (η). Which has to be chosen to guarantee not overshooting ...
2
votes
1answer
43 views

Using a 2nd neural network to predict 1st neural network prediction error

So for example, we are trying to predict the amount of rainfall in the afternoon base on continuous features such as humidity and temperature in the morning. 1st neural network: Regression neural ...
1
vote
2answers
82 views

The well-known classifiers that can be trained/tested in linear time [closed]

I am interested in collecting the list of the classifiers that (depending on their setting) can have linear time complexity (both in training and testing step) with respect to the number of samples $n$...