Skip to main content

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
1 vote
1 answer
98 views

Meaning of "error on the test point x" in optimal classifier for binary classification

Let f(x) be optimal classifier for binary classification where output is modelled noisy. What does it mean "f(x) makes a mistake only if there is an error on the test point x"? Basically, ...
DSPinfinity's user avatar
1 vote
1 answer
112 views

Is it possible to do machine learning on encrypted images?

I wuold like to know if it is possible to train a CNN to classify images (like nsfw detection) without receiving any intelligible information about it ? By applying some kind of one-way mask before ...
max-lt's user avatar
  • 111
1 vote
2 answers
224 views

The training process of a conditional GAN

For example, consider a dataset like MNIST. I give the conditional vector to produce only the number $7$ for both the generator and discriminator. In the following scenarios, what will the ...
user avatar
2 votes
2 answers
204 views

Can mini-batches for stochastic gradient be balanced but not representative of the training data?

When we construct mini-batches for stochastic gradient, it is important to ensure that the different mini-batches are balanced (for example, in case of classification they contain the same ratio for ...
DSPinfinity's user avatar
1 vote
0 answers
38 views

Neural network learns to mimic distribution of classes in dataset instead of using signal from input

I'm trying to implement example from a classic AI paper named "Learning representations by back-propagating errors" by Hinton et al. Example aims at training network able to predict third ...
Jan Grzybek's user avatar
2 votes
1 answer
82 views

NLP "small" model to improve "big" model

When training the model for NLP is it important to get rid of data which has "bad semantic" for learning process? My plan is to create a "small model" which can decide whether data ...
Milkmaid's user avatar
  • 135
-2 votes
1 answer
68 views

the best choice to reduce a features vector

i have 1200 features highly correlated , and i want to reduce those number of features so the best choice is use feature selection or dimensionality reduction? and which method is the best in this ...
myriamkach's user avatar
1 vote
1 answer
42 views

How can we construct a skewed noise distribution using the maximum likelihood approach?

When the probability of observing a large positive error is larger than the probability of observing a large negative error in binary classification, how can this be modelled by a skewed noise ...
DSPinfinity's user avatar
1 vote
1 answer
129 views

Why is laplace distribution less sensitive to outliers than normal distribution?

Why is laplace distribution less sensitive to outliers than normal distribution?. The following is the content. (See page 103 of http://smlbook.org/book/sml-book-draft-latest.pdf) "Also, in the ...
DSPinfinity's user avatar
0 votes
1 answer
90 views

What is the potential issue of nested neural networks

everyone. I am working on a nested neural network architecture. For the sake of better understanding my question, simply assume the loss is $L = G(k’) - H(k'')$ where $G$ and $H$ are two functions we ...
Zuba Tupaki's user avatar
0 votes
0 answers
24 views

When to know if I am "on the right track" for a CNN architecture

Context Very new to CNNs and ML in general. I am building a simple binary image segmentation network for generating black and white image masks (white pixels = desired object; black pixels = all else)....
gladshire's user avatar
0 votes
0 answers
20 views

kerascv retinanet for gender identification

I am using KerasCV Retinanet to detect people and their genders in images. I would like to detect "man", "woman", "boy", "girl" and "baby" in images. ...
Doug's user avatar
  • 25
1 vote
1 answer
71 views

Unclear steps in derivation of normal equations in linear regression using linear algebra approach

How are eqs.(3.55) and (3.56) obtained? Especially, it is unclear how triangle inequality implies eq.(3.56) because we have squared norms.
DSPinfinity's user avatar
0 votes
0 answers
10 views

Using Variable Text Features in Machine Learning Model

I am building a classification model using deidentified patient data with ICD-10 codes as inputs. Each code is a string and represents a diagnosis, and these follow the pattern of 1 letter, followed ...
Omnitragedy's user avatar
0 votes
1 answer
313 views

In the conditional GAN (cGAN) architecture, why does the discriminator need conditional variable?

I'm reading about conditional GAN (cGAN) architecture, what I know is that the generator creates images combining both noise vector and conditional variable, the noise vector brings in random elements ...
user avatar
3 votes
2 answers
529 views

Why can we have misclassifications for a perfect model in logistic regression?

I am reading the book: MACHINE LEARNING- A First Course for Engineers and Scientists, by Lindholm et.al. Chapter 3, page 50. Link: http://smlbook.org/book/sml-book-draft-latest.pdf Consider the ...
DSPinfinity's user avatar
0 votes
1 answer
109 views

Why is my agent stuck on the same action in my Twin Delayed Deep Deterministic Policy Gradient (TD3) program?

I've been tirelessly converting a reinforcement learning program from Python to JavaScript using TensorFlow.js that is running Twin Delayed Deep Deterministic Policy Gradient (TD3). I'm just trying to ...
CloudZero's user avatar
3 votes
1 answer
74 views

Regression loss conditioned by the ground-truth values

I'm working on a regression problem with a CNN in which the input is a single image, and the output is an angle in degrees (which determines a specific measure related to the image). Sometimes, the ...
Cezoz08's user avatar
  • 43
2 votes
1 answer
1k views

Neural network for game

There is a game for two, which is an NxN field (always the same size). Players take turns. The first player's goal is to connect the two points (not necessarily at the corners) given on this field. ...
user3576767's user avatar
0 votes
1 answer
47 views

If the unigram precision is (N-1)/N, then the bigram precision is :

Consider the following machine translation scenario. The reference translation has N words (do not consider sentence beginner ‘hat’ and sentence finisher ‘dot’). The machine output also has N words. ...
Geeklovenerds's user avatar
1 vote
1 answer
65 views

What is the concept of pruning a tree in Machine Learning regression problems?

What is the concept of pruning a tree in Machine Learning regression problems? I am confused and a simple explanation would be great.
Shekhar's user avatar
  • 11
0 votes
1 answer
534 views

Generator loss not decreasing while training GAN

I’ve been attempting to create a basic GAN to generate images using this database of flowers (https://www.robots.ox.ac.uk/~vgg/data/flowers/102/). I’ve spent a few days on this, and largely based my ...
Hozaifa Bhutta's user avatar
0 votes
0 answers
27 views

I'm trying to build image search like Google Photo-Image with face is given to model & it'll get all the images in database in which he/she is present

When a user upload a selfie, the model search same person in dataset of images of multiple persons and get back all the images in which that person is present. Step 1: From dataset of images I detect ...
BKP's user avatar
  • 1
0 votes
0 answers
12 views

Classes definition for detecting impervious surfaces on aerial photographies

My project is to use deep learning, essentially a UNET segmentation model, to detect impervious surfaces on high resolution aerial photographies. I wonder if it's better to train the model with many ...
Below the Radar's user avatar
1 vote
1 answer
46 views

What number classes makes a classification problem continuous

I am working on a classification problem, where I have sequences of images and I want to train a model to predict the index of the image with some wanted property. The target classes would obviously ...
mavex857's user avatar
1 vote
1 answer
100 views

Feature vector representation of probability distribution

I have a series of multiple probability distribution like this: [ [0.2, 0.3, 0.5], [0.1, 0.2, 0.7], ... ] Do you have any suggestions how I can represent this ...
mavex857's user avatar
1 vote
1 answer
85 views

Why can't one get extremely high accuracy with an machine learning algorithm?

Suppose we have a classical machine learning problem. Say $m$ training examples and $n$ features with $m >> n$. Suppose I find a great algorithm using automl or otherwise that gives 95% accuracy ...
wander95's user avatar
  • 113
0 votes
0 answers
14 views

How can a RNN with 256 cells accept a input of any size?

I built a 3 layered RNN model with 256 cells each using torch. Input feature size is set to 40. Below give a basic Idea on the model. ...
D Star Let's Explore's user avatar
1 vote
1 answer
29 views

ML predicting output based on single feature

I am a beginner in ML, I came across the below scenario. I wonder if I could use ML (and which kind) and what would be the the steps needed for the pre-processing of a time-series. So first (1)how to ...
jet's user avatar
  • 21
0 votes
0 answers
8 views

I have n-dimensional latent representational data, with a y logit label: How do I find peaks in the data using the label?

I essentially need a "find peaks" algorithm for when the input data is n-dimensional. Specifically, in the latent space of my neural network I have have collected all the training data ...
Eoin Ó Coinnigh's user avatar
0 votes
0 answers
36 views

How (or can) you formulate the Fisher information matrix in terms of a loss function, specifically cross-entropy loss?

I recently saw the following formulation of the Fisher information matrix in a paper on Transformer pruning: $$ \mathcal{I} := \frac{1}{|D|} \sum_{(x,y) \in D} \left( \frac{\partial \mathcal{L}(x,y;1)}...
premed's user avatar
  • 1
1 vote
0 answers
146 views

In the figure of Stable Diffusion, when does the switch part change?

In the illustration of Stable Diffusion, there is a concatenation part through Cross-Attention. Why is there a switch in the concatenation part?
diffusion stable's user avatar
0 votes
1 answer
126 views

How to interpret Tom Mitchell's definition of machine learning?

I quote the well known definition: A computer program is said to learn from experience E with respect to some class of tasks T and some performance measure P, if its performance on T, as measured by ...
ado sar's user avatar
  • 169
-2 votes
2 answers
130 views

Can the multiclass classification be modified to binary classification for better accuracy [closed]

I've achieved good accuracy in binary classification problems, but I'm facing challenges when it comes to multi-class classification tasks. While tackling a natural language processing challenge ...
Raghul Azhagaiah's user avatar
1 vote
1 answer
72 views

Unclear points in scaled Euclidean distance

The following is from a machine learning book. I did not understand the explanation given in the figure caption. Could some expert make it clear? Why is the stretching class-dependent for the center ...
DSPinfinity's user avatar
1 vote
1 answer
80 views

What is $\mathbf{S}$ (sample covariance matrix) in image compression based on PCA?

If the feature vector is $\mathbf{x} \in \mathbb{R}^{d}$, then to apply PCA we first need to construct the "sample covariance matrix) \begin{align*} \underbrace{\frac{1}{N}\sum_{i=1}^N(\mathbf{x}^...
DSPinfinity's user avatar
0 votes
0 answers
19 views

Does machine learning philosophy translate into action effectively?

Can anyone tell me how to understand the machine learning philosophy as a guide to the effective use of AI for activism and organizing?
eristosca's user avatar
1 vote
2 answers
66 views

Is geodesic distance between two similar photos less than the Euclidean distance between them? If so, why?

This is from a ML book: "Principal component analysis, which we discussed in section 6.3, works when the data lies in a linear subspace. However, this may not hold in many applications. Take, for ...
DSPinfinity's user avatar
0 votes
0 answers
17 views

Why is k=1 in linear discriminant analysis for two classes?

With two classes, why does Linear Discriminant Analysis (LDA) consider only projecting onto one dimension (k=1)? Normally, even with 2 classes, you can consider projecting the d-dimensional original ...
DSPinfinity's user avatar
1 vote
0 answers
81 views

Pointers to (deep) latent variable models that admit analytical approximations

I am aware that there is a plethora of deep generative models out there (e.g. variational autoencoders (VAE), GANs) that can model high-dimensional data as the images of latent variables under a non-...
ngiann's user avatar
  • 111
1 vote
1 answer
59 views

Do "procedurally generated" images use a set of base images to generate new images (as AI generated images do)?

I am new here, and apologize if this question is off-topic. I know that AI generated images are based on a set or database of real images created by real artists. In game development, I have heard of ...
Job_September_2020's user avatar
0 votes
0 answers
14 views

Why is $z$ considered a random variable in the following formulation of Locally Linear Embedding Problem?

The following is the derivation of "Locally Linear Embedding Problem" from the book Machine Learning, 4-th edt, page 152, by E.Alpaydin. Why is $z$ considered a random variable so that $E(z)...
DSPinfinity's user avatar
1 vote
0 answers
40 views

How do LGBM rankers train?

I'm looking into Learning to Rank models - specifically, the LGBMRanker model - and I want to understand how it's able to train. It takes in features, group sizes and labels, and optimizes for a ...
Shirish's user avatar
  • 403
0 votes
1 answer
129 views

Time Series Classification using Transformer Encoder

Lets say I have a collection of tensors, each tensor representing a time series with 64 points and 4 features. The dimension of each tensor would be [64,4]. I am trying to classify these series. For ...
Zohaib Hamdule's user avatar
0 votes
0 answers
12 views

Does the order of iteration affect the answer returned by FIND-S?

This paragraph is from the book Machine Learning by Tom M.Mitchell (Page 26): Initialize $h$ to the most specific hypothesis in $H$ For each positive training instance $x$ $\;\;\;\;\;\;$.For each ...
Emad's user avatar
  • 215
-1 votes
1 answer
45 views

Is model order of a model class (for example, polynomial regression class) a hyperparameter or a tuning parameter?

We know that in ML we have tuning parameters and hyperparameters. Is model order of a model class (for example, polynomial regression class) a hyperparameter or a tuning parameter?
DSPinfinity's user avatar
0 votes
0 answers
32 views

Training YOLO on YOLO results

I have a large unlabelled dataset. What if I use YOLO to label it? Will this dataset be useful to train a better YOLO model? What if I then finetune it on a smaller labelled dataset? My usecase ...
Karol Idaszak's user avatar
1 vote
1 answer
39 views

Is there validation data in K-fold cross-validation?

We know that in machine learning the dataset is divided into 3 parts: training data, validation data and test data. On the other hand, K-fold cross-validation is defined as follows: the dataset is ...
DSPinfinity's user avatar
0 votes
1 answer
91 views

Realizability Assumption: Why is that for every ERM hypothesis $L_{S}(h_{S})=0$

I'm quoting Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014: Definition 2.1 (The Realizability Assumption). There exists $h^{\star} \in \mathcal{H}$ s.t. $...
Tran Khanh's user avatar
0 votes
0 answers
31 views

Why does in feature embedding the similarities between instances in the new space respects the original pairwise similarities?

Below is a statement from Machine Learning book, by E. Alpyadin, 4th edition, page 131: Question: Why does in feature embedding the similarities between instances in the new space respects the ...
DSPinfinity's user avatar

1 2 3
4
5
48