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.

932 questions
Filter by
Sorted by
Tagged with
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: ...
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 ...
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 ...
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 ...
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,...
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 ...
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 ...
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 ...
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"?
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 ...
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 ...
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 ...
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 ...
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 ...
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 ...
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, ...
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 ...
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/...
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 ...
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.
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 ...
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 ...
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 ...
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 = (...
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 ...
98 views

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 ...
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 ...
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 ...
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 ...
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 ...
95 views

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 ...
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 ...
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" ...