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
0 votes
0 answers
63 views

Drum sound classification using RNN issues - help needed

I am new to the field of machine learning, even tho I have solid background in semi-related fields (am control system engineer by trade) and as a hobby project I wanted to work a bit with sound ...
APasagic's user avatar
0 votes
0 answers
28 views

Do neural networks have a perception of space, regardless of dimensionality?

Suppose I have a model M which outputs a three-dimensional tensor of size 3x3x3. I have another model N which outputs a one-dimensional tensor of size 27. Train both models on some arbitrary objective ...
schmixi's user avatar
2 votes
1 answer
64 views

Could LLMs perform the autoregressive generation with probability vectors instead of choosing a discrete token every time?

As I understand it, GPT-style LLMs take a sequence of tokens as input and output a token probability vector. The first thing that happens to an input token is that it goes through the input embedding, ...
MelonDude's user avatar
0 votes
1 answer
41 views

Machine Learning Algorithm for identifying the factors contributing to academic performance of students

I have a dataset with several qualitative and quantitative attributes, including age, location (longitude, latitude), city, parent occupation, family size, GPA etc. My task is to find the attributes/...
Dawood Ahmad's user avatar
0 votes
2 answers
190 views

How the Q,K,V be calculated in multi-head attention

I want to understand the transformer architecture, so I start with self attention and I understand their mechanism, but when I pass to the multi-head attention I find some difficulties like how ...
LAILA EL OUEDEGHYRY's user avatar
2 votes
2 answers
460 views

Is it easier to use back-propagation or genetic algorithms to teach an artificial intelligence?

I am making a very simple neural network for a school project, and I would like to know what the best and easiest way to "teach" a neural network would be. From what I know, backpropagation ...
AlexanderB's user avatar
0 votes
0 answers
27 views

Distribution Based Mapping of Augmented (Noisy) Image and Clean image?

I have a task of training a Denoising Autoencoder which will be augmented MNIST dataset and and I have to reproduce the clean image, I have to use the ResBlocks in the Encoder(Conv Layer) as well as ...
Jivitesh's user avatar
0 votes
0 answers
11 views

Adding Feature in HGNN to Count Connections to Types of Nodes

So I'm making a HGNN currently in which the number of connections a node has to other nodes of a certain type matters. Its a social network, so I care about how many person-person connections a person ...
Daniel Eban's user avatar
0 votes
1 answer
32 views

Can/should a reward function depend on something other than state in a DQN

Question: Is it OK to have a reward function on a DQN or any RL algorithm that depends on variables other than the enviroment state? I'm asking because, so far I'm learning from tutorials, but I've ...
Oliver Mohr Bonometti's user avatar
0 votes
0 answers
22 views

Is it necessary that the number of samples of one class be balanced with other classes in a classification problem?

Consider a classification problem using machine learning techniques (e.g. malware detection). In such a problem, is it necessary that the number of samples from each class (in the mentioned example, ...
user16385455's user avatar
1 vote
0 answers
64 views

What is the best way to train a neural network with a variable number of inputs?

Suppose I have a neural network with 5 inputs: [A,B,C,D,E] There is only 1 output. The expected accuracy of the model should increase when all 5 inputs are ...
user18959's user avatar
0 votes
1 answer
54 views

What ML/DL algorithms for frequency spectrum pattern classifications?

I have a set of known frequency spectrum data for this set of chemical compounds. Then the unknown Y is the mixture of some of these compounds. The task is to determine what compounds are in this ...
David293836's user avatar
4 votes
2 answers
1k views

Why different noise in GAN generate different images?

I understand that noise $z$ serves as the input to the generator. Noise $z$ is essentially a vector of random numbers, typically from Gaussian distribution with chosen size of like $100$. However, I ...
user avatar
1 vote
0 answers
83 views

How do transformer-based architectures generate contextual embeddings?

How do transformer-based architectures like Roberta generate contextual embeddings? The articles I've read keep saying that transformer encoders work bidirectionally. Because of self-attention, they ...
user avatar
4 votes
3 answers
187 views

In the VAE, why is $z \sim \mathcal{N}(\mu, \sigma^2)$ equivalent to $z = \mu + \sigma \odot \epsilon$?

In the reparameterization trick of a Variational Autoencoder (VAE), instead of sampling noise $z$ from $z \sim \mathcal{N}(\mu, \sigma^2)$, we can use a different method: $z = \mu + \sigma \odot \...
user avatar
1 vote
1 answer
92 views

Fine tuning or just feature extraction or both using Roberta?

I'm reading a program that use the pre-trained Roberta model (roberta-base). The code first extracts word embeddings from each caption in the batch, using the last hidden state of the Roberta model. ...
user avatar
1 vote
1 answer
71 views

What kind of language in theory of computation language includes current LLMs?

We obviously know that Turing machines are enough for current LLMs training and inference. Are there languages behind the hierarchy that are enough for these processes (e.g. context-sensitive ...
sw.'s user avatar
  • 111
1 vote
1 answer
47 views

Using the definition of APAC learning and uniform convergence in practice

I am currently studying "Understanding Machine Learning from Theory to Practice" written by Shai Shalev-Shwartz and Shai Ben-David. I want to understand how i can use the Definitions and ...
MathAccount12's user avatar
0 votes
1 answer
177 views

What does it mean to "learn a distribution", and what does it contain?

When I was reading about discriminative vs generative models, I came across their definitions: Given a distribution of inputs $X$ and labels $Y:$ Discriminative models learn the conditional ...
user avatar
1 vote
1 answer
42 views

Beginner need help - identify data [closed]

I am learning Tensorflow, and I have a specific problem I want to solve. I want to identify on/off of my large power consumers at home. And calculate the power consumption elsewhere. I expect to input ...
povlhp's user avatar
  • 11
0 votes
0 answers
18 views

Enhancing Soil Moisture Predictions Using Multimodal Data Integration in Agriculture

I am exploring an interdisciplinary research area involving multimodal data, focusing on agriculture. My study incorporates both visual and tabular data: crop and soil images from three distinct ...
Md Rakib's user avatar
4 votes
1 answer
142 views

Notation used in paper on Continuous Time Reinforcement Learning

I am working on implementing the learning shown in this paper: https://homes.cs.washington.edu/~todorov/courses/amath579/reading/Continuous.pdf In the paper, the authors devise a continuous time ...
Derick Diana's user avatar
2 votes
1 answer
75 views

Is it a requirement/recommendation to normalize my inputs into [0,1] range?

All features of my input dataset, which is going to be used for training a simple multi-layered neural network, are in range $[-1,+1]$ and the output of $NN$ is a single number again in range $[-1,+1]$...
Bikay's user avatar
  • 23
0 votes
2 answers
42 views

What might be the suitable machine learning algorithm to train a model suitable for forecasting a patient's urine output?

The task involves developing a machine learning model trained on urine output trends, clinical parameters, medications, and fluid input of patients to predict their future urine output. What machine ...
Rajat Srivastav's user avatar
0 votes
0 answers
25 views

Does reducing the image dimensions before sending them to Language Models (LMs) significantly affect the processing time?

I am currently working on utilizing Language Models (LMs) to describe images in my project (Search Engine for AI images). However, I am wondering about the efficiency of the process, particularly in ...
Oleksandr G's user avatar
4 votes
1 answer
53 views

Likelihood function for Gaussian Discriminant Analsis

Im trying to understand how the likelhood function for gaussian discriminant analysis is derived. I self studying Murphy's Probabilistic Machine learning, and in it, he states the likelihood function ...
turtle_in_mind's user avatar
1 vote
2 answers
281 views

What technique is used for training Large Language Models like GPT?

I'm learning about GenAI, such as GPT (Generative Pretrained Transformer), and I'm particularly interested in understanding the training techniques used for these models. Deep learning, generally, can ...
Exploring's user avatar
  • 353
0 votes
1 answer
38 views

ML Model for Route Optimization in Manufacturing

I am looking for a ML Model for route optimization within a factory. I am starting simple with optimizing 1 aisle (2 rows). We have a bunch of criteria, and it would be dependent on the data at that ...
Discover's user avatar
0 votes
0 answers
18 views

Extracting features from multiple curves

I am building a model that predicts the SOH of a lithium ion battery. My data are from 600 battery charge cycles as follows: for each cycle I have 3 curves each of length 128 samples: voltage, current ...
deckard1992's user avatar
1 vote
2 answers
79 views

"a good model (with low loss) is one that assigns a high probability to the true output $y$ for each corresponding input $\mathbf{x}$"?

Chapter 1.2.1.6 Maximum likelihood estimation of Probabilistic Machine Learning: An Introduction by Kevin P. Murphy says the following: When fitting probabilistic models, it is common to use the ...
The Pointer's user avatar
1 vote
1 answer
27 views

Since $f_c$ returns the probability of class label $c$, we require $0 \le f_c \le 1$ for each $c$, and $\sum_{c = 1}^C f_c = 1$. Why avoid this?

Chapter 1.2.1.5 Uncertainty of Probabilistic Machine Learning: An Introduction by Kevin P. Murphy says the following: We can capture our uncertainty using the following conditional probability ...
The Pointer's user avatar
1 vote
1 answer
169 views

Marking object on a map from the image

I have been researching if there are any existing machine learning models that would help mark objects (for example: cars) on the map having only image, camera location, and camera orientation. For ...
user3500960's user avatar
0 votes
1 answer
44 views

Gradually increasing CPU load on using sentence embeddings model with kmeans

I am having a ML based production application, using flask, deployed on GCP server using gunicorn workers. In each incoming request, a text sentence is received. It is using sentence transformers (All-...
racdev's user avatar
  • 1
1 vote
1 answer
74 views

Is there a theoretical way to determine the best learning rate for gradient descent if the function is a simple known polynomial?

I was playing around gradient descent topic. Wrote a function that calculates a gradient descent of a degree-2 polynomial. While trying out what is the best "step size multiplyer" (a.k.a. &...
Ababababa's user avatar
  • 113
2 votes
2 answers
155 views

How Xavier Initialization formula works

In the research paper on Xavier initialization what is the purpose of putting $n_{in}$ and $n_{out}$ under 2 and added them it just says as a compromise but it is not exactly a harmonic mean or an ...
Stef's user avatar
  • 95
0 votes
0 answers
72 views

What are the differences between Inception Score and Fréchet Inception Distance?

From the articles I've read about image generation using GANs, the Inception Score measures two things simultaneously: the variety of images (diversity) and the distinct quality of each image. Does ...
user avatar
0 votes
0 answers
45 views

Find the relationship between data in this plot

Attached image. How would you find the relationship between independent variable (x) and dependent variable (y)? Is it linear or non-linear? What would the function looks like? P.S. I believe this is ...
DLCVIP007's user avatar
0 votes
1 answer
60 views

Why would balancing be so helpful when the imbalance is minimal?

I have a binary classification problem with a modest-to-none class imbalance (33% positive class-66% negative class). When I don't impose class balance, my XGBoost model produces no positive class ...
bonzo_pippinpaddle's user avatar
2 votes
1 answer
96 views

How are POMDPs solved in practice?

In the literature that I've seen so far on how to either exactly or approximately solve POMDPs (Partially-Observable Markov Decision Processes), there seems to be a lot of focus placed on maintaining ...
QMath's user avatar
  • 123
0 votes
0 answers
50 views

Where I can find SOTA models of information retrieval?

Can someone tell me where I can find SOTA models of information retrieval? My task is to rank documents by given query by semantic search of embedding. I know that models like ColBERT, SPLADE solve ...
prostak's user avatar
  • 113
0 votes
0 answers
30 views

Which main steps should I consider in order to successfully use a VAE for Anomaly Detection?

I am thinking about using the variational autoencoder model for anomaly detection . I have an Android Logs dataset. As the logs generated are a representative of time series type of data I thought ...
MLenthusiast's user avatar
1 vote
0 answers
36 views

How to correctly train policies in multi-agent RL?

I am diving into Multi-Agent Reinforcement Learning and after reading some literature, I would like to clarify some approaches because I am not quite sure. Now for the following two cases it is clear ...
thsolyt's user avatar
  • 11
1 vote
0 answers
44 views

Classifying Images that Look Like Noise

I'm about to build a system that is supposed to evaluate images (900 x 150) like the following and classify it in to one of five categories: image that looks like noise In case you're wondering, they'...
Ed Park's user avatar
  • 11
5 votes
1 answer
707 views

How can the discriminator determine the sample is fake or real?

Based on the articles I've read, the discriminator can identify whether a sample is fake or real. However, the articles don't clarify the conditions used to determine if a sample is fake or real. I ...
user avatar
2 votes
1 answer
95 views

What are meaning of parameters $\theta$ in this context?

I'm reading the article about generative model from Open AI, here is the section where they explain them: Our network is a function with parameters $\theta$, and tweaking these parameters will tweak ...
user avatar
1 vote
1 answer
108 views

How to make a model forget specific training it has received?

Does L1/L2 (NAdam weight decay) really make the model "unlearn"? Ok so my question might be dumb but is there any way to "unlearn" a model - and yeah I know there is wieght_decay ...
AnArrayOfFunctions's user avatar
0 votes
0 answers
43 views

Explanation for the expression of positional encoding in NeRFs

I was reading the NeRF paper recently (https://arxiv.org/pdf/2003.08934.pdf), and under the positional encoding section, I see that the authors propose usage of the following function for transforming ...
user185887's user avatar
1 vote
0 answers
24 views

What is the right way to make a neural network learn a period function with known period

I want a neural network to learn the representation of a periodic function whose period is known to be $T$. What is the correct way to achieve that? From my reading, I could infer two things: This ...
user185887's user avatar
0 votes
0 answers
15 views

Feature engineering - filter out columns based on linear correlation result

Besides the other factors (such as domain knowledge), is there any rule of thumb or best practices to keep/remove features that were identified with high correlation between each other? The problem is,...
Echo's user avatar
  • 101
0 votes
0 answers
20 views

Executing Multiple ML Models simultaneously on multiple cores to reduce the model building time

I have a time series forecasting problem which consist of date, item no and quantity columns. I have defined a function which takes input as data frame and forecasting period (Daily,Weekly,Monthly,...
Rohit's user avatar
  • 1

1
2
3 4 5
48