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
2
votes
1answer
25 views

Why can't we mimic a dog's ability to smell covid?

As far as I can tell, we have invented tools and algorithm to: Detect a wider range of colors at a larger range than humans or any other animals on the planet Detect sound with wavelengths ...
0
votes
1answer
40 views

Dimension Reduction - Which feature should remove to reduce the dimension of the matrix

Let's suppose that we have the following 2 tables: If we want to reduce the dimension by one(in every table) which feature we should remove and why ? I am confused about the way that i should work ...
0
votes
1answer
24 views

Is any of the assumptions hold true for the mentioned?

Suppose the use of linear regression. The result of the MSE is 120.5(mean squared error) for the train-set. Wev'e reached the minimum of training the data. Is it possible that by applying Lasso(L1 ...
0
votes
0answers
44 views

Is it true that machine learning is pretty much math than actual programming?

I have recently started reading books about AI and machine learning and this is what I think of it so far: A lot of people have the assumption that AI is just a bunch if ...
1
vote
1answer
118 views

Asymptotic analysis for machine learning algorithms

I wanted to know if it would practical and useful to analyse machine learning algorithms in terms of asymptotic computational complexity. I have noticed this is very uncommon. However, I believe it ...
1
vote
1answer
169 views

What does “Temporal extent” mean?

I am reading Long-term Temporal Convolutions for Action Recognition and under the Section 3.1, I read this: To investigate the impact of long-term temporal convolutions, we here study network inputs ...
94
votes
7answers
19k views

Why is deep learning hyped despite bad VC dimension?

The Vapnik–Chervonenkis (VC)-dimension formula for neural networks ranges from $O(E)$ to $O(E^2)$, with $O(E^2V^2)$ in the worst case, where $E$ is the number of edges and $V$ is the number of nodes. ...
-1
votes
1answer
22 views

Batch size of CNN for training

I'm doing CNN with UNet. When training UNet with batch-size of 128, validation_accuracy did not increase, it looks converged around 50 %. But, once I decreased it to 64, training looks fine. What is ...
-1
votes
1answer
48 views

Kohonen, 1 dimension, SOM, puzzle

We consider training one-dimensional open map of Kohonen with neurons in one-dimensional input space. We assume it is completed the phase of the device and the weights $w_i$, $i = 1,2, \dots, N$, are ...
1
vote
0answers
19 views

Why do we use different cost functions in machine learning?

In most machine learning applications, we use Maximum Likelihood Estimation to derive appropriate cost functions. For example, if we assume that our model $f(x;\theta)$ yields the mean of a ...
2
votes
1answer
15 views

Basic exercises on decision trees

I am a pure math person doing some ML self-study and I am pretty lost. I am trying to solve the following exercises on decision trees: Exercise 1. Consider the following training set where $X_1,X_2,...
2
votes
1answer
38 views

Expressivity of neural networks, how much information can be stored

I want to know whether a given neural network (with a finite number of nodes) is able to store all injective maps f: D -> C, where D has cardinality k and C has cardinality N (so the number of maps ...
1
vote
1answer
52 views

Method for combining derivative free optimization results of different data inputs

I am working on an algorithm that has multiple fixed parameters. The algorithm analyzes time series data and spits out a number. The fixed parameters need to be such that this number is as small as ...
0
votes
0answers
26 views

CNN and relearning

I was suggested to post my question here... An original my question is https://stackoverflow.com/questions/66421719/cnn-and-relearning I would like to train my network with CNN. My image data set is ...
0
votes
1answer
81 views

Batch sizing for convolution neural networks — powers of 2 or powers of primes?

The conventional wisdom for convolution neural networks (CNNs) is to make the batch size a power of 2 because of hardware utilization/optimizations done in the convolution layers. A similar logic ...
0
votes
0answers
20 views

Does Linear Discriminant Analysis make dimensionality reduction before classification?

I'm trying to understand what LDA exactly does when used as a classifier, i've understood how the dimensionality reduction works and i've understood that the classification task is carried out with ...
0
votes
0answers
26 views

why divide norm of w in svm

So I get this through the math behind the SVM (Support Vector Machine), and I get this formula $$(w^T)(x_1-x_2) = 2.$$ We then divide both side with norm of $w$ then we get the new formula $$ \frac{w^...
0
votes
1answer
193 views

Pac learnable when changing distribution

if H is Pac learnable according to Definition 3.1 (PAC Learnability) A hypothesis class H is PAC learnable if there exist a function $m_H\colon(0,1)^2 \mapsto N$ and a learning algorithm with the ...
5
votes
1answer
154 views

What algorithm do SVMs use to minimize their objective function?

Support Vector Machines turn machine learning linear classification tasks into a linear optimization problems. $$ \text{minimize } J(\theta,\theta_0) = \frac1n \sum_1^n \text{HingeLoss}(\theta,\...
1
vote
1answer
55 views

What kind of bigram probability smoothing is this?

I hope it isn't off topic but I need to understand this example. Given the corpus 12 1 13 12 15 234 2526 and smoothing factor of ...
0
votes
1answer
34 views

Confused on Variational AutoEncoder

I'm a bit confused on how Variational Autoencoders are trained. In particular I'm confused on how the latent variable is generated for each input. My questions are as follows: When running ...
0
votes
0answers
8 views

Which model to apply on such panel data with so may rows but for each unique id rows are 6-8 rows per unique id?

I am new to such panel data where I have multiple observation for same ID in different Quarter and I am not sure what kind of machine learning algorithm I can apply. I have data from Q1-18 till Q4-...
0
votes
0answers
43 views

deep learning - is loss value should be divided by `seq_length`

I'm new to deep learning and I'm looking at train.py here: https://github.com/huanghao-code/VisRNN_ICLR_2016_Text/blob/master/train.py. I run this code and the loss ...
0
votes
0answers
7 views

How is the dimensionality of the volume in ConvNets determined for a general case?

In ConvNets, I understand how the dimensionality of a flat image changes after convolving it with a single filter. For example, if you convolve a P x P x 1 image (assume no padding) with a filter with ...
0
votes
1answer
64 views

Can you share some pointers to get better at working alone in projects?

I am an ML Engineer who works alone in projects most of the time. I don't have people who are much smarter than me working alongside. Most of the time, I feel that working alone is a tedious job,one ...
0
votes
0answers
24 views

Looking for references for real-world scenarios of data-poisoning attack on labels while doing supervised learning

Consider the following mathematical model of training a neural net : Suppose $f_{w} : \mathbb{R}^n \rightarrow \mathbb{R}$ is a neural net whose weights are $w$. Suppose during the training the ...
0
votes
1answer
18 views

Is there an online/offline tool that can perform K-means/median, given an initial centroid from the user?

The types of problems I am trying to solve are as follows: Given a set of co-ordinates such as: (1,2), (3,3), (6,2), (7,1), a value of k such as k=3 and an initial set of centroids such as c1=(2,2) ...
0
votes
1answer
17 views

Signal translation with Seq2Seq model

I'm currently doing some research on signal processing and I got a dataset which includes the signal in itself and its "translation". So I want to use a Many-to-Many RNN to translate the ...
0
votes
2answers
29 views

Can the perceptron classifier achieve perfect accuracy, on any data set?

I was thinking. Since any data can become linearly seprabale through kernel methods, meaning there is a dimension where this data is linearly seprable, so feed this processed data set into the ...
1
vote
0answers
12 views

What is spatial information in neural network? [duplicate]

The architecture of the CNN model contains several convolutional layers, non-linear activations, batch normalization, and pooling layers. The initial layers learn the low-level concepts such as edges ...
0
votes
1answer
129 views

Computer Vision Techniques to find Slope of beach in the 2D Images?

What I am planning to do is to calculate the height and estimate the slope of the segmented Object. The camera will be static and the Object of Interest is the slope of the beach. I am finding harder ...
0
votes
1answer
28 views

Is it possible to do face recognition with just the eyes?

Assuming the input photo is focused on a person's face, if the person is wearing a surgical mask, most face recognition software fail to identify the subject's face. Most facial landmark models are ...
1
vote
1answer
22 views

Is transfer learning applied on only similar datasets only?

I am trying to make a CNN model on different brands of logos . Firstly , I wrote a CNN from scratch and trained it on which I got 70% accuracy, I have total 40 classes and each class has 100 images . ...
1
vote
1answer
51 views

How does Gradient Descent treat multiple features?

As far as I know, when you reach the step, in a gradient descent algorithm, to calculate step_size, you calculate ...
1
vote
0answers
22 views

Even distribution of weighted sums across a period of time

I want to automatically&optimally split and distribute a number in several buckets as evenly as possible across a period of time. Example: 5000 across 12 months, in 6 buckets, with weights 15%, ...
0
votes
1answer
37 views

Mapping categorical data in K-nearest neighbour

I have a data set which contains categorical data, for example: ...
1
vote
0answers
33 views

Reinforcement learning and Graph Neural Networks: Issue with entropy [closed]

I am currently working on an experiment to link reinforcement learning with graph neural networks. This is my architecture: Feature Extraction with GCN: there is a fully meshed topology with ...
0
votes
1answer
13 views

Conditional probability in Expectation Maximization (EM)

I've got the following equation: $p(j = 1 | x, \theta) = \frac{p(j=1,x | \theta)}{p(x | \theta)}$ Why does it hold? Or maybe, how do I use Bayes Theorem in this case, i.e. if we do not only have $p(j =...
1
vote
0answers
46 views

Best algorithm/model to establish relevance between events utilizing mixed data type (Tags, Time, x_coordinate, y_coordinate)? [closed]

I'm building a relevance ranking system for incidents occurrence and prevention. My goal is to use four attributes to establish relevance: tag (About 500 tags), x_coordinate, y_coordinate and time. ...
0
votes
1answer
13 views

What exactly is label noise?

I've been doing research on precollege summer programs, and one ongoing project that has come up is "Improving Label Noise Robustness with data Augmentation and Semi Supervised Learning". So,...
0
votes
0answers
15 views

Are Learning Classifier Systems considered (learning) agents?

Does a LCS model a learning, rule-based agent or does a LCS just implement the agent program (mapping of inputs to actions)? According to Russel & Norvig : agent = architecture + agent program ...
1
vote
1answer
48 views

What is the Number of epochs with no improvement after which training will be stopped.?

I am trying to make a Convolutional neural network. Training the images of different brands of Logos. Have 100 images per class and there are 40 classes. I have trained the model now want to check ...
0
votes
1answer
36 views

How does CNN deal with rotation invariant pictures?

I am trying to make a CNN model . Training the image . Want to know that When we apply kernel on image and take out the features of images. That features are rotation invariant or we have to apply ...
0
votes
1answer
379 views

How do you calculate the training error and validation error of a linear regression model?

I have a linear regression model that I've implemented using Gradient Descent and my cost function is a Sum of Squares Error function. I've split my full dataset into three datasets, a training set, a ...
3
votes
2answers
3k views

Q-learning in a Dynamic environment

I am new to reinforcement learning. Lately, I have learned Q-learning using the following tutorial. Is Q-learning still possible if the environment is dynamic. Using the environment of the tutorial ...
19
votes
3answers
8k views

Line separates two sets of points

If there is a way to identify if two sets of points can be separated by a line? We have two sets of points $A$ and $B$ if there is a line that separates $A$ and $B$ such that all points of $A$ and ...
0
votes
0answers
13 views

How do I choose the right model for production?

I am trying to build a classification algorithm having 28 classes. These classes consists of Logo of companies like adidas , Nike etc. I have very low dataset below than 100 images and greater than 70 ...
0
votes
1answer
67 views

Weighting function for Non Uniform Learning

Consider a hypothesis class $H = \cup_{n=1}^{\infty} H_n$, where for every $n\in N$, $H_n$ is finite. Find a weighting function $w : H ->[0, 1]$ such that $\sum_{h \in H} w(h) ≤ 1$ and so that for ...
1
vote
1answer
31 views

Which pretrained model will be best for my dataset?

I am trying to build a classification algorithm having 28 classes. These classes consists of Logo of companies like adidas , Nike etc. I have very low dataset below than 100 images and greater than 70 ...
0
votes
0answers
30 views

Human brain controlled computer

It is already possible to let a computer drive the human brain to some limit like for example in the medical world, but will it be possible to let the human brain control a computer system by directly ...

1
2 3 4 5
22