Questions tagged [machine-learning]

For questions related to machine learning (ML), which is a set of methods that can automatically detect patterns in data, and then use the uncovered patterns to predict future data, or to perform other kinds of decision making under uncertainty (such as planning how to collect more data). ML is usually divided into supervised, unsupervised and reinforcement learning. Deep learning is a subfield of ML that uses deep artificial neural networks.

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

Universal function approximation theorem on 10000 different functions

I have a NN which is trying to learn 10,000 different delay functions based on the coordinates of the matrix it exists in (a 100x100 matrix, each cell containing a different function.) By a different ...
0
votes
1answer
108 views

multi vs one prediction using Regression

I was trying to build a prediction system where I have the input data arranged in multiple columns. The input data would be of the type where I have weather, service type (bronze, silver, gold), size ...
1
vote
0answers
39 views

The results changed even though seed is fixed [closed]

I am using a reinforcement learning model for some tasks. and for the model, I am using stable_baselin3 and for the environment, I am using the gym. I made a small change in the environment and the ...
2
votes
1answer
56 views

A model for each sub-problem vs one model for the whole problem

Let's say one wants to use a neural net to learn some function $g(x)$. Let's say that we know that $g$ is a combination of two functions (or two sub-problems), $g(x)=f_2(f_1(x))$, and that we have two ...
0
votes
0answers
26 views

How to predict the possible next moves of cars from given first moves?

I want to find the next moves of cars from the previous moves, but I could not figure out what should I use as an algorithm. Can you help me to find a way to solve this problem? I have a lot of car ...
2
votes
1answer
41 views

What is the relevance of the concept size to the time constraints in PAC learning?

My question is about the relevance of concept size to the polynomial-time/example constraints in efficient PAC-learning. To ask my question precisely I must first give some definitions. Definitions: ...
1
vote
1answer
40 views

What does the complexity equation constitute exactly in “Why Should I Trust You?” LIME paper

I've recently been reading this paper on LIME, an algorithm to interpret ANY machine learning model. I encountered this equation (in red) on page 4 and have just been having a hard time deciphering ...
4
votes
1answer
113 views

Which neural network can I use to solve this constrained optimisation problem?

Let $\mathcal{S}$ be the training data set, where each input $u^i \in \mathcal{S}$ has $d$ features. I want to design an ANN so that the cost function below is minimized (the sum of the square of ...
4
votes
2answers
198 views

Mathematical foundations of the ability to learn

I am an undergraduate student in applied mathematics with an interest in artificial intelligence. I am currently exploring topics where I could do research. Coming from a mathematical background I am ...
1
vote
1answer
24 views

Does a second-order fully-connected layer have any uses?

I was thinking about implementing second-order regression via a fully-connected layer, and I came up with this: $X$ is the input data, shaped $(features, batch\_number)$. $w0$ is the bias, shaped $(...
0
votes
1answer
208 views

Wind speed forecasting using ARIMA model in Python3 [closed]

Recently, I started working on time-series models and would mention that I am very new to python and ML as a whole. I tried to implement a time-series model on wind speed data. Being a newbie, I ...
2
votes
2answers
366 views

Face liveness detection using face landmark points

How to detect liveness of face using face landmark points? I am getting face landmarks from android camera frames. And I want to detect liveness using these landmark points. How to tell if a human ...
0
votes
0answers
61 views

What are the different possible usages of the word "i.i.d" in machine learning?

The acronym "iid" stands for "independent and identically distributed". It is a property of a sequence of random variables. You can read here for more details. This question is ...
6
votes
3answers
1k views

Which functions can't neural networks learn efficiently?

There are a lot of papers that show that neural networks can approximate a wide variety of functions. However, I can't find papers that show the limitations of NNs. What are the limitations of ...
1
vote
1answer
44 views

Can I always interpret features as random variables in machine learning safely?

Consider the following statements from Chapter 5: Machine Learning Basics from the book titled Deep Learning (by Aaron Courville et al.) Machine learning tasks are usually described in terms of how ...
3
votes
4answers
726 views

What is the fundamental difference between an ML model and a function?

A model can be roughly defined as any design that is able to solve an ML task. Examples of models are the neural network, decision tree, Markov network, etc. A function can be defined as a set of ...
3
votes
1answer
183 views

Where do the feature extraction and representation learning differ?

Feature selection is a process of selecting a subset of features that contribute the most. Feature extraction allows getting new features that are not actually present in the given set of features. ...
0
votes
1answer
42 views

Which data representation of text as input for NLP Deep Learning models?

I have been given a data set with 30.000 text documents (each text file is rather small with respect to its length and consists in most cases of around 20 sentences), which are labelled with 0 or 1. ...
0
votes
1answer
22 views

Selecting class weights for loss function

I have a machine learning task where I would like to weight losses based on the frequency of the categorical values appearing in the data. The binary solution can be seen below, but I'd like to know ...
1
vote
1answer
24 views

Why do terms in the computation of state space size scale exponentially?

The image below is from a Berkeley AI course pdf I found. My question is, why do the terms accounting for the ghosts and pellets come in raised to the number of units? For example, there are two ...
1
vote
0answers
29 views

Are RNN a good approach to solve this type of problem?

I have a problem that can be optimized by taking five actions, and finally, after a series of steps to achieve a solution. The actions (1 to 5) are picked randomly. A time-step (epoch) is concluded ...
0
votes
2answers
62 views

What would be a typical pre-processing and data normalization pipeline for time series data (for non-linear models such as neural networks)?

I've started to work on time series. I was wondering what would be the best data normalizing and pre-processing technique for non-linear models, specifically, neural networks. One I can think of is ...
1
vote
1answer
64 views

Do we train a logistic regression model using a dataset that is 3 times bigger than the validation dataset?

Suppose we have a data set $X$ that is split as $X_{\text{train}}$, $X_{\text{val}}$ and $X_{\text{test}}$ and the outcome variable is binary. Let's say we train three different models (logistic ...
1
vote
1answer
44 views

Is logic AI a complement to learning AI?

I want to know the relation between logic AI and learning AI. Logic AI here refers to the branch of AI that is based on mathematical logic. Learning AI refers to the branch of AI that is based on ...
0
votes
1answer
56 views

Does the Bayesian MAP give a probability distribution over unseen t*?

I'm working my way through the Bayesian world. So far, I've understood that the MLE or the MPA are point estimates, therefore using such models just output one specific value and not a distribution. ...
0
votes
0answers
22 views

Minimizing hard and soft margin objective functions in a one dimensional SVM

Given a one-dimensional training dataset with 3 points, 2 negative points at -1 and 1, and a positive point at 0 (as in the picture above): (a) What solution would minimize the linear Hard Margin SVM ...
1
vote
1answer
75 views

Is my flowchart a good representation of the perceptron learning algorithm?

I made a flowchart for a simplified perceptron leaning algorithm. Here is the process of the learning algorithm. Initialize the weights first. Get a training example randomly and make a prediction. ...
0
votes
2answers
65 views

How can I cluster based on the complementary categories?

K-means tries to find centroid and then clusters around the centroids. But what if we want to cluster based on the complement? For example, suppose we have a group of animals and we want to cluster ...
2
votes
1answer
297 views

Finding patterns in binary files using deep learning

I am a newbie in deep learning and wanted to know if the problem I have at hand is a suitable fit for deep learning algorithms. I have thousands of fragments each of about 1000 bytes size (i.e. ...
0
votes
1answer
50 views

Attention mechanism: Why apply multiple different transformations to obtain query, key, value

I have two questions about the structure of attention modules: Since I work with imagery I will be talking about using convolutions on feature maps in order to obtain attention maps. If we have a set ...
2
votes
1answer
1k views

Why can the learning rate make the loss increase in stochastic gradient descent?

In Deep Learning by Goodfellow et al., I came across the following line on the chapter on Stochastic Gradient Descent (pg. 287): The main question is how to set $\epsilon_0$. If it is too large, the ...
3
votes
1answer
134 views

How can I build an AI with NLP that read stories [closed]

I want to do an NLP project but I don't know if it's doable or not as I have no experience or knowledge in NLP or ML yet. The idea is as follows: Let's say we have a story (in the text) that has 10 ...
0
votes
0answers
30 views

Limit of momentum update equation

I am self-studying on optimization algorithm on https://d2l.ai/chapter_optimization/momentum.html and couldn't get my head around some derivation: Instead of the standard gradient descent update ...
-1
votes
0answers
35 views

Deep learning and machine learning [duplicate]

If I was Given a set of large training examples (xi,yi), how can training a neural network (NN) via stochastic gradient descent differs from using regular gradient descent in terms of the mathematical ...
0
votes
1answer
59 views

How can I implement 2D CNN filter with channelwise-bound kernel weights?

I would like to bind kernel parameters through channels/feature-maps for each filter. In a conv2d operation, each filter consists of HxWxC parameters I would like to have filters that have HxW ...
1
vote
0answers
30 views

Which machine learning algorithm can be used to identify patterns in a large file of numbers?

I'm new to machine learning and have many questions, but today I want to know if my case can be solved by machine learning, and if the answer is yes, I would like to know what to learn first and which ...
2
votes
2answers
153 views

What is the difference between game theory and machine learning?

What is the difference between game theory and machine learning? I had gone through the papers Deep Learning for Predicting Human Strategic Behavior, by Jason Hartford et al., and When Machine ...
0
votes
1answer
49 views

Is there a way to use AI to compare thousands of files and detect the ones containing "unusual" content?

Is there a way to use python and AI to compare thousands of files and detect the ones containing "unusual" content? Those files are supposed to have "homogeneous" configuration ...
0
votes
2answers
234 views

Why does k-means have more bias than spectral clustering and GMM?

I ran into a 2019-Entrance Exam question as follows: The answer mentioned is (4), but some search on google showed me maybe (1) and (2) is equal to (4). Why would k-means be the algorithm with the ...
2
votes
1answer
111 views

An infinite VC dimensional space vs using hierarchical subspaces of finite but growing VC dimensions

I have the following scenario. I have a binary classification problem, whose underlying function is a step function. The probability distribution of feature vectors is a uniform over the domain. Case ...
0
votes
2answers
32 views

Given embedding vector A and vector B, how to find top k embedding vectors such that they are similar to vector A and dissimilar to vector B

Which would be better approach for getting top k embedding vectors such that they are similar to embedding vector A and dissimilar to vector B. Approach 1: calculate ...
6
votes
1answer
281 views

An intuitive explanation of Adagrad, its purpose and its formula

It (Adagrad) adapts the learning rate to the parameters, performing smaller updates (i.e. low learning rates) for parameters associated with frequently occurring features, and larger updates (i.e. ...
1
vote
1answer
63 views

Aside from specific training sets, what distinguishes the capabilities of different AI implementations?

(Disclaimer: I don't know much about ML/AI, besides some basic ideas behind it all.) It seems like ML/AI models can often be boiled down to statistics, where certain levers (weights) get fine-tuned ...
14
votes
3answers
351 views

Why does Batch Normalization work?

Adding BatchNorm layers improves training time and makes the whole deep model more stable. That's an experimental fact that is widely used in machine learning practice. My question is - why does it ...
4
votes
1answer
63 views

Is non-negative matrix factorization for machine learning obsolete?

I am taking a course about using matrix factorization for machine learning. The first thing that came into my mind is by using the matrix factorization we are always limited to linear relationships ...
4
votes
1answer
204 views

How do I determine which variables/features have the strongest relationship with each other?

This is my problem: I have 10 variables that I intend to evaluate two by two (in pairs). I want to know which variables have the strongest relationships with each other. And I'm only interested in ...
1
vote
2answers
49 views

How to make NN distinguish between two types of functions (data)?

I have a neural network which is trying to predict two types of functions in a noisy setting. The input is an array, and the output is also an array. The two types of functions I am trying to predict ...
0
votes
1answer
42 views

Can anyone please explain TFLite quantization part found in Netron neural network viewer?

I was checking tflite file in Netron. There I found the quantization formula in Netron as below: quantization: 0.007709330413490534 * (q + 3) I know the ...
1
vote
1answer
571 views

Machine learning to predict 8*8 matrix values using three independent matrices

Problem Statement I have 4 main input features. This is a small snippet of the data for clearer understanding. Gate name -> for example AND Gate index_1 -> ...
4
votes
2answers
468 views

What are the differences between softmax regression and logistic regression (other than when the number of classes is 2)?

I read about softmax from this article. Apparently, these 2 are similar, except that the probability of all classes in softmax adds to 1. According to their last paragraph for ...

1
2 3 4 5
38