Episode #125 of the Stack Overflow podcast is here. We talk Tilde Club and mechanical keyboards. Listen now

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
3
votes
1answer
353 views

CURE algorithm: what does moving the representative points towards the centroid do?

The CURE algorithm is a method of clustering data. An outline of it can be found here on slide 5: https://www.slideshare.net/ellepiu/cure-clustering-algorithm. I personally learnt it from this video: ...
2
votes
1answer
258 views

How is adversarial autoencoder better than an ordinary autoencoder?

An adversarial autoencoder helps us to impose a prior distribution $p(z)$ on the encoded values of the inputs, or $q(z)$. On the contrary, an ordinary autoencoder (which we train like an ordinary ...
1
vote
0answers
71 views

Understanding Time Series Data for Classification

I have collected data from numerous volunteers driving a simulator in 8 different scenarios (classes). A volunteer drives in a map for 4 minutes in one scenario (one experiment), then he drives in the ...
0
votes
1answer
45 views

Why the negative reward function in linear quadratic regulation encourage to be at original state?

I was reading Stanford's CS 229 materials on Linear Quadratic Regulation ( Lecture note 13, youtube Lecture 18, around time 36 min). And it mentions that: " the quadratic formulation of the reward is ...
3
votes
1answer
284 views

Are the No Free Lunch theorems useful for anything?

I have been thinking about the No Free Lunch (NFL) theorems lately, and I have a question which probably every one who has ever thought of the NFL theorems has also had. I am asking this question here,...
-1
votes
1answer
39 views

How is ReLU used in machine learning functions

I've seen how sigmoid would be used in machine learning sigmoid(dot(activations, weights)-bias) like this ^ but sigmoid makes sure your values are between 0 and ...
0
votes
1answer
91 views

Perceptrons: Functions not learnable without bias

I am trying to determine which functions are not learnable without a bias when building a perceptron. The set of functions I need to evaluate is {NOT, OR, AND}. Could someone help interpret these ...
-1
votes
1answer
39 views

Using computer vision instead of algorithms?

I have been thinking of a problem i have here with a calendar scheduler where i basically want to split a year into seconds and have access to the dataset of whole year. In this year i assign blocks ...
0
votes
2answers
158 views

Is machine learning a subarea of expert systems?

My question is short and straightforward: Can be considered "machine learning" a subarea of "expert systems"?
1
vote
1answer
108 views

Machine learning - PCA and KNN on rgb images are too slow

I work with python and images of tables (taken from above). My aim is to take a photo of a random table and then find the most similar tables to it in my database. By most similar I mean tables of ...
1
vote
0answers
111 views

Recurrent neural networks (Hopfield-like) with short limit cycles

Standard Hopfield networks exhibit stable patterns (states) which are attractors of a dynamic system. I wonder how to modify standard Hopfield networks such that they exhibit stable limit cycles as ...
2
votes
0answers
75 views

Simulated annealing upper bound seems way too high

In a nutshell I found this paper that provides an upper bound for the amount of iterations we expect before visiting the global optimum at least once. (It then uses that number to find a lower bound ...
1
vote
0answers
287 views

Using machine learning to detect trend reversal in a time series [closed]

I'm starting to learn machine learning, and have honed in on a problem to get my hands dirty with: how to detect a trend reversal in a time series. I've asked this question on stats.SE more than a ...
1
vote
0answers
33 views

suggestion for optimization problem with $\ell_{2,1}$ norm and Frobenius norm

Suppose I derive my application problem as the following type of optimization problem: $$\min_X ||X||_{2,1}+||X^\top||_{2,1}+||X-A||_F,$$ where $X$ is a (square) matrix, $A$ is a constant matrix. I ...
1
vote
0answers
24 views

Need a game with AI techqniques [closed]

I want to learn Artificial Intelligence techniques by writing a game (or maybe any fun project). Can you suggest any games? Consider that I'm a beginner in AI, but have basic knowledge Algorithms and ...
3
votes
4answers
1k views

Efficiently labelling training data in machine learning

Obviously it always depends on the specific case. However, my question is how to label data efficiently without writing a source code from scratch which solves the final problem itself? For example, ...
3
votes
0answers
79 views

Was there a phase in Machine Learning timeline when researchers thought some Neural Networks could not be trained?

I was talking to a professor who made a comment to my question. Me: So much of quality literature around this topic ( IP Protection for Neural Weights) emanated in 1990-1991, I'm truly at loss ...
2
votes
0answers
15 views

Induction / (machine learning) of Resource Grammars for Grammatical Framework?

Grammatical Framework is based in Abstract Categorial Grammars. It is known that Combinatory Categorial Grammars have grammar induction/learning capabilities see e.g. https://link.springer.com/article/...
5
votes
2answers
219 views

How does machine learning relate to artificial intelligence?

For example, is it a subset? Are they two separate fields in Computer Science? I have hear conflicting information: one professor said they are synonyms. However, in the courses taught at Stanford ...
0
votes
0answers
19 views

undefined alphabet of observations in HMM

how to represent an observation matrix if we do not have a defined observation alphabet? I'm working on extraction of data in a text.
6
votes
1answer
115 views

What is the role of Numerical Gradient Computation in Backpropagation algorithm?

I was listening CS231n (2017) lectures and noted that there is a lot of attention to Numerical Gradient Computation (NGC). It starts @5:53 in this video and appears a few times later. Also, looking ...
1
vote
0answers
199 views

Distributing Neural Network Training World-Wide Using Blockchain?

I just finished reading a white-paper from a recent AI startup. The company, Deep Brain Chain, wants to distribute neural network training over computers worldwide, using blockchain technology. Here ...
2
votes
2answers
98 views

How deep do neural networks need to be?

My question is a bit on the philosophical side, and there is probably not one single 'correct' answer on this. Nonetheless, I'm curious to hear your opinion... I'm currently designing a convolutional ...
2
votes
2answers
215 views

Regularization term moving the hyperbolic plane

When we train a network, we usually have an error function which usually looks like this: $$Error = (output - target)^2$$ When we add a regularization term, it looks something like this: $$Error = (...
3
votes
1answer
61 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 ...
1
vote
0answers
98 views

adjusted fitness in NEAT algorithm

I'm learning about NEAT from the following paper: http://nn.cs.utexas.edu/downloads/papers/stanley.ec02.pdf I'm having trouble understanding how adjusted fitness penalizes large species and prevents ...
2
votes
0answers
24 views

How often should I read out information from an echo state recurrent neural network?

Recurrent neural networks makes it possible to implement some kind of memory, which can be very useful for a lot of tasks, incl. (but not limited to) robot control, which I am interested in. For ...
0
votes
0answers
39 views

Fast hill climbing algorithm that can stabilize when near optimal

I have a floating point number x from [1, 500] that generates a binary y of 1 at some ...
0
votes
0answers
14 views

List of metrics for dates

I am given a set of pairs of dates and would like to extract features I can put into an machine learning algorithm. Thus far I have already written two different metrics, however I didn't find much ...
1
vote
1answer
30 views

How to figure out whether two texts refer to the same object or event

Let's assume there is something happen in the world - Football world cup final. And team-1 beat team-2 with the score 3:2. So there is whole bunch of articles on every website about it, each contains ...
1
vote
1answer
122 views

Exploration in reinforcement learning when state space is huge

When the state-action space is huge I know I can use function approximators to generalize but how can I explore? Doing an exhaustive search seems very naive. What DeepMind for example did to explore ...
5
votes
1answer
95 views

VC dimensions: Let ${x_1, \ldots, x_N}$ be $N$ labelled points on $\mathbb{R}$, then there exists a sinusoid that separates these points

(Proposition, pg 26): Let ${x_1, \ldots, x_N}$ be $N$ points on $\mathbb{R}$, $N \in \mathbb{Z}$, labelled either $+1$ or $-1$ , then there exists a function from the set $\{t \mapsto \sin(\omega t)| \...
1
vote
0answers
55 views

Rule-based targeting algorithm

I'm working on a project that needs an advertisement targeting algorithm. I don't know much about the space, so I'm here to ask how to get started. The interesting thing about this problem is that I ...
0
votes
2answers
272 views

What are the drawbacks of Normalized Mutual Information clustering evaluation method?

What are the drawbacks of Normalized Mutual Information (NMI) clustering evaluation method? For evaluating what clustering algorithms, is the NMI evaluation method suitable?
0
votes
0answers
50 views

Can simple recurrent neural networks be remedied with higher precision floating point numbers?

I am of the understanding that tradition "simple" recurrent neural networks have the problem of "losing error" after a lot of time steps. But is this some kind of deficiency of the math, or the ...
0
votes
1answer
394 views

What is the time and space complexity of Rete algorithm

I am working on pattern matching algorithm. Its working and using very less memory. For the comparison, I have to compare it with the Rete Algorithm. I have checked it in the thesis of the author, ...
2
votes
0answers
28 views

Can machine learning be used in this scenario?

I'm keen to learn more about machine learning, as I feel it could be something that might have its uses in my place of work. I write PC software that controls scientific instruments, and one of its ...
1
vote
0answers
43 views

Detecting shapes using CNNs in respect to other shapes in the image

I'm solving a problem of detecting an optic disc in a retina image. As you can see from the image: the optic disc is the epicentrum of the blood vessels, has an irregular circular shape and has a ...
3
votes
1answer
80 views

What are some research papers or techniques that deals with fitting clothes on a human?

Given an image of a dress (from different angles), what could be ways to fit it on a human image (again multiple angles corresponding to dress)? Any link to research papers or tutorial regarding this?
1
vote
0answers
128 views

Can CNN be used for “unknown correlated” data?

Now the title may be misleading, but I don't know how to give it a better name. My question is if I have data in a 2d matrix and under the assumption that: -I know for sure that there are ...
1
vote
1answer
72 views

Terminology - Ensemble or Bag of classifiers?

I am working on a classification problem. My algorithm involves splitting the data into several subsets based on a specific feature (e.g. number of XX) then training a classifier on each of these ...
1
vote
1answer
1k views

How one epoch completes in Perceptron?

I am confusing on completing one epoch, I am using Single Layer Feed Forward neural Network approach. Lets suppose i have a data of OR Gate: ...
5
votes
1answer
189 views

Why does the effectiveness of my reinforcement based neural network recede after a while?

I have a reinforcement based neural network training on the OpenAI gym CartPole-v1 environment. For the structure and training algorithm, assume it is the same as the one in this article. Typically, ...
1
vote
1answer
63 views

Bayesian updating for multivariate Gaussian

I am reading http://www.yisongyue.com/courses/cs159/lectures/LinUCB.pdf and come across this slide What has been confusing me boils down to showing that multivariate Gaussian is conjugate to itself ...
0
votes
1answer
263 views

maximizing inner product of vectors in an ellipsoid and a given vector

I have been wrestling with this for quite a long time but couldn't convince myself that the following is true: What I do understand: $\theta_a$ denotes the set of points that are within the ellipsoid....
1
vote
0answers
181 views

If we can train a ML algorithm to recognize letters with 95% accuracy, why does OCR software still suck? [closed]

So I've seen all these leaps in machine learning alorithms these past years and they've only gotten better and better at recognizing handwritten text. I remember reading once that some algorithms have ...
2
votes
1answer
35 views

Detecting face like patterns using CNN based face detector

I have a CNN based object detector trained on WIDER Face dataset. It can successfully detect human faces in a given image. Now, I am trying to detect abstract face and minimalistic face patterns in ...
2
votes
2answers
60 views

Machine Learning: if test, validation errors are same, the model with lower train loss is better at generalization?

I tuned some hyperparameters and got 2 best models. These two models are almost the same "test(not train)" and "validation" errors. But model A has lower "train" ...
0
votes
0answers
132 views

Why solutions for Normal form Ordinary least squares and Linear Regression are different

I am trying to apply Linear Regression method for a dataset of 9 sample with around 50 features using python. I have tried different methodology for Linear Regression i.e Closed form OLS(Ordinary ...
2
votes
3answers
2k views

VC Dimension of Origin-Centered Circle

Is the VC dimension of an origin-centered circle 1 or 2? It seems to me that the VC dimension of an origin centered circle should be 1, because for two points with distances from the origin r1 <= ...