Questions tagged [artificial-intelligence]
Artificial Intelligence (AI) is a topic in computer science that deals with the study / creation of intelligent machines. Use this tag for on-topic questions that have an AI aspect.
315 questions
0
votes
1
answer
28
views
GNNs with higher order adjacency matrices
Usually, the adjacency matrix stores information about direct connections of nodes in a graph.
The information from k-th neighbours is passed-on at k-th layers of GNNs, as described in the original ...
0
votes
0
answers
30
views
Backward-forward algorithm for HMM
I understand the derivation of forward-backward algorithm in HMM.
However, when I try to derive a backward-forward algorithm in HMM( simply the reverse direction of original algorithm), I encountered ...
1
vote
1
answer
40
views
Generalization error as U shape curve with respect to model complexity (bias variance tradeoff))
Is there any work mathematical rigorously prove that the generalization error for certain learning problems exhibits U shape curve with respect to model complexity (bias variance tradeoff)? Any ...
- 233
4
votes
0
answers
40
views
How Does a 95% Energy Reduction in Neural Networks Affect Accuracy and Efficiency?
Earlier this month, a fascinating paper was published on arXiv:
"Addition is All You Need for Energy-efficient Language Models"
The authors propose an algorithm, $\mathcal{L}\text{-Mul}$, ...
- 65.8k
0
votes
0
answers
22
views
Apart from Recurrent Neural Networks what are some alternatives to AR(n), ARIMA(p,q) models?
I want to write a master thesis in CS (Machine learning). The topic that was assigned to me was time series prediction. I want to compare different ML methods with statistical methods (AR,ARIMA). I am ...
- 1
0
votes
0
answers
7
views
What is the best architecture for multi-target text regression?
I'm building an AI model using Google's 'Civil-Comments' dataset. It has 7 different labels, each a float than can be anywhere from 0 to 1. Embedding Bags, which I have read about. do not perform well....
0
votes
0
answers
24
views
Choosing an evaluation model for LLM for Question and Answering
I was learning the basic of LLM evaluation and the framework introduced in one of the short courses in Deep Learning AI was to generate samples of question and answer which act as the ground truth. ...
- 1
1
vote
0
answers
100
views
Multidirectional propagation of biological neurons - could/should we recreate it e.g. with joint distribution neurons? [closed]
While ANNs are rather trained for unidirectional propagation, action potential propagation in biological neurons is symmetric e.g. ”it is not uncommon for axonal propagation of action potentials to ...
- 431
6
votes
1
answer
173
views
What advantage do sinusoidal positional encodings have over binary positional encodings in transformer LLMs?
I've recently come across an article that discusses the reasons why large language models use sinusoidal functions to generate positional encodings — as per the famous paper Attention Is All You Need (...
- 156
1
vote
1
answer
91
views
How can we implement pipelines using LLMs that can consider information from the internet in their responses?
Let us suppose that we are implementing a data processing pipeline based on LLMs and, in some part of the process, we need to search the internet for finding relevant information regarding some topic, ...
- 1,008
0
votes
0
answers
39
views
How should I approach calculating sample size for number of raters required for a study?
I am proposing a study for evaluating reports generated by 3 human experts vs 3 different LLMs on a set of 10 situations. Basically, we're trying to whether the human experts are better or if the LLMs ...
- 13
2
votes
0
answers
29
views
Time Series Anomaly Detection with Class Variables
In ("univariate") time series anomaly detection, what techniques are there to incorporate class variables?
For example, in accounting transactional data, we might care about anomalies in the ...
- 73
1
vote
1
answer
137
views
Convolutional Neural Networks - Flattening with multiple feature maps
I have a very simple question about CNNs, which I unfortunately couldn't find an explanation for.
Imagine we have a CNN, that has four filters (eg right, left, top, bottom edges) each of those outputs ...
- 13
0
votes
0
answers
27
views
Low MSE between the vectors but different distribution
I have two output tensors whose MSE is really small (0.04) but on checking the distribution of the tensors they are very different.
I am using:
torch.nn.MSE(output_tensor, input_tensor) = 0.04
I am ...
- 121
2
votes
1
answer
311
views
How to address bias in AI Image Recognition Model: Oversampling, Undersampling, and Ensemble Techniques Not Working
I am currently working on an image recognition project using AI, but I am facing challenges with bias in my model's predictions. The model seems to be biased toward the majority classes in my dataset. ...
0
votes
0
answers
41
views
How this is possible? Test loss is under train
I got this graph for my loss.
As you can see the distance between the two graphs is so much!
Can we say it shows bias is large and it's underfitting?
Is this thing that I just said true or isn't true?...
- 101
1
vote
0
answers
28
views
Dataset for Swimming with Heartbeat and Motion Data [closed]
I am currently working on my final project CS degree that involves analyzing swimming data, specifically focusing on both heartbeat and motion data. I am looking for a dataset that includes these two ...
- 11
1
vote
1
answer
66
views
Understanding bias-variance tradeoff decomposition
This is the formula :
$E[(Y−f^2)]=σ^2 +Bias^2[f^]+Var[f^]$
What i cant understand , the expectation is over the training Set for a fixed $x_0$ , thus the
$E(ϵ^2) =E(ϵ(x_0)^2) = ϵ(x_0)^2$ and not $...
2
votes
0
answers
80
views
Does a 1x1 convolutional Layer have a bias (Inception Modules)?
This question is regarding to the 1x1 convolutional layer idea from the paper
"Going Deeper with Convolutions"(https://arxiv.org/abs/1409.4842) that describe the idea of so called inception ...
- 21
-1
votes
1
answer
90
views
Machine learning and Artificial intelligence algorithms in identifying and classifying Airplane parts
Airplane parts and functions
Can Machine Learning and Artificial intelligence Algorithms assist in identifying and classifying Airplane images parts?
- 119
1
vote
0
answers
47
views
Machine learning and Natural Language Processing Algorithms for Indian Surnames Homophones [closed]
Homophones
Indian Surnames List
English last names
Can machine learning, Natural Language Processing (NLP), Artificial intelligence assist in classifying , interpreting and specifying the differences ...
- 119
3
votes
1
answer
128
views
Minimizing the expected loss (PRML)
In Bishop's PRML in section 1.5.2, the author introduces a loss function for classification, which is the expected loss,
$$
E[L]=\sum_k \sum_j \int_{R_j} L_{kj}p(\textbf{x},C_k)d\text{x}
$$
where Lkj ...
0
votes
0
answers
24
views
Should the mean of NN's predicted values match the mean of the original values?
I built a neural network model in R using the Keras' package and for some reason, the mean of the predicted values of the neural network doesn't match the mean of the original values. For every other ...
- 61
1
vote
1
answer
96
views
entries into machine learning, deep learning, artificial intelligence for social scientists
As far as CrossValidated allows users to ask for reference,
does anyone know (top-notch, authoritative) books, resources, or references about ML, DL, or AI for social scientists?
If there are still &...
9
votes
1
answer
1k
views
What is the roadmap to self-taught probability and statistics for artificial intelligence?
I am trying to self-teach probability and statistics for Machine Learning career. However I want to learn very well as doing research in AI is my goal.
Which books should I use to learn probability, ...
1
vote
1
answer
297
views
Neural Networks - Can I Use Any Activation for the Output Layer?
I'm new to neural networks, and in almost everything I'm reading, the activation function recommended on the output layer follows a specific pattern:
If the network does binary classification (1 ...
- 111
4
votes
2
answers
688
views
Reinforcement learning needs dataset?
Sorry for this dummy question based on the number of contents in the field that I am asking about but
It seems that there are tons of texts and videos explaining what ...
- 147
1
vote
1
answer
54
views
Can there be 3 initial weights for 2 inputs in a backpropagation network?
I am fairly new to machine learning and Neural Network. I was given a scenario where there is a 2-input single unit backpropagation Neural Network has 3 initial weights. The inputs are x and y. The ...
- 11
5
votes
2
answers
638
views
Can I apply a confusion matrix to classification tasks outside of ML?
I would like to know if it's possible to use a confusion matrix to measure the performance of a classification tool outside the realm of ML or a statistical model.
For example, if I had a small script ...
- 51
1
vote
0
answers
68
views
Tic tac toe AI, general questions
Tl;dr - Very new to AIs and neural networks, trying to make tic tac toe. Trying to use a genetic algorithm that plays against other AIs, and the looser leaves. They seem to never learn even to not ...
- 31
6
votes
3
answers
2k
views
If dropout is going to remove neurons, why are those neurons built?
I know that Dropout will remove neurons randomly to reduce over-fitting.
If Dropout is going to remove neurons, why are those neurons built? We could remove those neurons from the architecture.
Why ...
- 226
2
votes
2
answers
3k
views
Using AI for human like mouse movement between two points
I am trying to use Neural Networks or ML to make my mouse cursor move as humanly as possible, I want to be able to generate a set of points which are needed for the mouse to move from point A (...
-2
votes
1
answer
37
views
Are Deep Learning and GPUs changing the game? [closed]
"Essentially, all models are wrong, but some are useful."
--- Box, George E. P.; Norman R. Draper (1987). Empirical Model-Building and Response Surfaces, p. 424, Wiley. ISBN 0471810339.
...
1
vote
0
answers
35
views
CT-Scan Classification Overfitting Problem
I am currently trying to train pretrained convolutional neural networks trained on the imagenet dataset to be able to classify ct-scans into two classes. Viral Pneumonia and Normal.
I am using K-fold ...
- 21
1
vote
1
answer
583
views
Splitting medical dataset by patient
I am currently trying to train a CNN model to classify CT-scans.
I split the dataset using K-fold cross-validation and since the dataset I am using contains multiple slices per patient, I split the ...
- 21
1
vote
1
answer
502
views
0
votes
2
answers
204
views
Which metric to use for language translation?
So I am using a pre-trained model to do the language translation
Eg:
Input = "Good morning"
Output = "Bonjour"
I would like to see if the ...
- 63
5
votes
1
answer
1k
views
Should I join train and validation sets for final NN model training? If yes, when to stop training the final model?
Normally we divide our dataset into 3 sets:
train set,
validation set,
test set.
We use train set to find optimal parameters (weights and biases of NN) and validation set to find optimal NN ...
- 51
1
vote
0
answers
110
views
What is Max Pooling?
What is Max Pooling and why would I use it?
There are a lot of questions about Max Pooling on Stack Exchange, but none of them explain what it is, why we want to use it, the problem it solves, or ...
- 111
1
vote
1
answer
52
views
The added value of Machine Learning compared to traditional rule based methods
I would like to showcase the value of machine learning compared to traditional rule based (symbolic AI) methods.
I would also like to break it down for Unsupervised, Supervised and Reinforcement ...
- 1,453
0
votes
1
answer
38
views
Can a DQN learn when to avoid actions?
Imagine there is a problem with 3 possible outputs: A, B and C. But, only output ...
- 145
6
votes
2
answers
380
views
What's the MAG of this underlying DAG?
I am studying causal discovery, with an interest on constraint-based algorithms like FCI (Fast Causal Inference).
I want to know what's the Maximal Ancestral Graph (MAG) of this underlying DAG (...
- 583
1
vote
1
answer
833
views
What is the difference between K-Nearest Neighbor and Adaptive K-Nearest Neighbor algoritms?
While studying KNN, I have come to see "Adaptive K-Nearest Neighbor algorithm" and I understand KNN but I wonder how "Adaptive K-Nearest Neighbor" work. I tried to find some ...
- 3,585
2
votes
1
answer
505
views
About "Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation"？
I am reading the Yoshua Bengio et al, Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation. After read this paper, I wonder how to establish a GFlowNet if I don't know ...
- 31
1
vote
1
answer
74
views
Question about the "sample" in "Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation"
I'm reading this paper recently. I'm confused about the "sample a distribution of trajectories" repeatedly mentioned in the article. I don't understand what this means. What is the sample ...
- 31
0
votes
1
answer
18
views
Best grouping rows method with Multi-Armed Bandit
I have a dataframe , here above a sample :
...
- 249
1
vote
1
answer
2k
views
Time series forecasting: classical methods vs. machine learning / artificial intelligence [closed]
Do you know papers that researched how accurate predictions are using time series or AI? I see more papers using VAR/VECM than XGBoost. Do you guys know why this?
- 31
2
votes
0
answers
44
views
Using Machine Learning to Create Periodic Paths
Question: How can I use Machine Learning to predict the right initial conditions $(P_0,V_0)$, given the angles of the triangular table, that will result in periodic paths in the triangular billiard ...
- 141
1
vote
1
answer
974
views
Why applying Grad-CAM to the input layer is not common?
Grad-CAM is a popular tool that could be applied to the last convolutional layer to understand the inner structure of the deep neural network.
It is general to apply Grad-CAM onto the last ...
김의담
0
votes
0
answers
491
views
Which is the correct ROC metric type to use for Imbalanced Dataset (macro,micro, weighted) for multiclass classification?
I am working on a classification task where I have more than 350 classes with HUGE data imbalance. I want to check my model performance but I am confused which metric to use. So I Googled some ...
- 244