All Questions

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

How to improve Accuracy on dermaMNIST dataset?

Unlike the regular MNIST which gets 97-99% with a fairly basic network, dermaMNIST gets training/validation stuck on 0.69. This tells me the model is underfitting. But, making it bigger seems to have ...
Zwerchhau's user avatar
4 votes
0 answers
62 views

Why did I got opposite results of the original "How transferable are features in deep neural networks" paper?

I got tasked with reproducing the results of the influential "How transferable are features in deep neural networks?" paper in a DL class I'm taking (Full code). I got the exact opposite ...
OfirD's user avatar
  • 91
0 votes
0 answers
23 views

Decision Tree prediction for the fail reason

In my experiment, I used Decision Trees to predict whether participants will pass or fail, and I will provide feedback to them based on the reason for their failure. The Decision Tree includes three ...
Leila Moradi Avargani's user avatar
0 votes
0 answers
17 views

Do categorical embeddings leak data in time series?

I am a bit confused on this matter, I can't find any resources that touch on the following but my logic says that embeddings do introduce data leakage in time series: Considering a temporal dataset ...
idontknowmuch's user avatar
1 vote
1 answer
16 views

Medical Predictive AI Model, Calibration Curve axes representation order

When representing calibration curves in a medical setting, usually they are represented the way they are in assays for lab analyses, where concentration analogue to "Fraction of Positives" ...
SmollPangolin's user avatar
0 votes
0 answers
14 views

Why can't I increase my GPU utilization?

I have a simple UNet model (~1M params) written in Keras 3.0.1, running with a torch backend. My CUDA version is ...
Savindi's user avatar
0 votes
1 answer
24 views

handling predictions with optional or missing features

We have a few variables that are highly predictive in our modeling task. Is it sound to train models with a superset of features even though some are known NOT to be available at predict time? & ...
eliangius's user avatar
  • 351
0 votes
0 answers
9 views

Fine tunning a model for question answering task without context on the dataset

So, i have a small dataset (contains around 2.5k question answer pairs).I want to fine tune T-5 base model on this question-answer dataset.Now, all the codes that i have came across they fine-tune ...
Nabid Hasan's user avatar
1 vote
0 answers
21 views

Uncertainty in stacked ensemble model

I am using the stacked generalization scheme to combine the predictions from different machine learning models (input models from now on). I am currently calculating the prediction interval for each ...
umbe1987's user avatar
  • 111
0 votes
1 answer
16 views

Group/cluster semantically similar classes in reports?

I'm fine-tuning BERT models to binary classify reports. For example, a report can be about 'birds' or not about 'birds'. This works really well, but now I want to do multi-label classification, ...
Rob Audenaerde's user avatar
0 votes
0 answers
10 views

real time anormal detection from surveillance footages

I'm implementing a model for real time anomaly detection from surveillance videos. so I need to notify the user when running the model if anomaly is detected. the model is trained for normal videos ...
Nimms's user avatar
  • 1
0 votes
0 answers
11 views

LSTM, different size for feature set and target

I am trying to build a weather forecasting model. X_train shape :(2970, 1, 9) Y_train shape : (3299675, 1, 4) I am following ...
Abhishek Patil's user avatar
0 votes
0 answers
2 views

Learning Theory - PAC learning, hypothesis class containing the true classifier

For a given hypothesis space $H$, assuming $f\in H$ where $f$ is the true classifier, you can choose a group $S~D$ where $D$ is a distribution, with a large enough sample complexity, such that the ...
Aishgadol's user avatar
  • 111
0 votes
1 answer
19 views

Why are some columns of feature matrix after dimentionality reduction zero?

I am trying to implement a paper in which the ultimate goal is to predict mutliple labels for instances (which are genes here). The feature matrix with shape of 1236*18930 is built by calculating term ...
Satarnejad's user avatar
0 votes
0 answers
12 views

If I do cross validation do I need to refit the model?

I am making a dual process. I have an initial dataset in which I train (fit) a model, then I do cross validation to get results. Until now everything normal, but additional to that, I create a new ...
Curious student's user avatar
1 vote
0 answers
27 views

Backpropgation for a single parameter on a rather simple network

Given the following network: I'm asked to write the backpropagation process for the $b_3$ parameter, where the loss function is $L(y,z_3)=(z_3-y)^2$ I'm not supposed to calculate any of the weights ...
Aishgadol's user avatar
  • 111
1 vote
1 answer
31 views

Why doesn't SciKit-Learn's KBinsDiscretizer's 'quantile' strategy distribute values evenly in the bins?

According to SciKit Learn's documentation for sklearn.preprocessing.KBinsDiscretizer, the quantile strategy is suppose the ...
Evan Aad's user avatar
  • 175
0 votes
0 answers
9 views

Generation of spectrum from features

In the field of chemical analysis, prediction of features, properties, is often done from spectra base on simple neuralnetwork and some AI models. But conversely, what methods are implemented to ...
tomtels's user avatar
  • 13
0 votes
0 answers
12 views

Keras Tuner for a (stacked) LSTM model?

I have a question about how to correctly setup a Keras Tuner model for a stacked LSTM model. What I have tried is the normal tutorial with a loop and the hp.Int() function to define the size of each ...
Barry's user avatar
  • 1
1 vote
0 answers
13 views

How to compare 55 models using AUC bootstrap confidence intervals?

I want to check if there is a difference in the confidence intervals of 55 models and select just one model. What should I do?
JAE's user avatar
  • 13
1 vote
1 answer
17 views

How to Balance Dataset extracted using image_dataset_from_directory

I'm new to tensorflow, so I've been trying to find the best way to do class balancing over a dataset where I used image_dataset_from_directory to load. But I haven't find the way to do it. I saw from ...
lopez-mgu's user avatar
0 votes
0 answers
21 views

Validation loss not decreasing

I am building a model for predicting stock portfolio positions, by minimizing a Sharpe loss function (corresponding to maximize the Sharpe ratio of the portfolio). The architecture is puting ...
Dan Lee's user avatar
0 votes
0 answers
14 views

How to select the subset which can represent the whole dataset

I have a time series of data for the whole year, which I need to run the analysis on Python. However, it takes a long time to run the model. I want to select a subset of data that can represent the ...
Thành Trần's user avatar
0 votes
1 answer
15 views

why do we have the "freedom" to set the gutter equations to +/-1 in SVM

Trying to understand SVM. I am sure that my reasoning can't be correct but I can't see what is wrong. We know that two points determine a line. I am trying to understand support vector machines using ...
onyourmark's user avatar
0 votes
0 answers
13 views

How to get probability of an outcome from skewed t distribution in R

I am trying to calculate the probability of stock return to be greater than X in next 28 days, using the skewed t-distribution as it fits the best to the ...
Krishnang K Dalal's user avatar
1 vote
1 answer
36 views

Сan we say that the regression problem is essentially a classification problem with an infinite number of classes?

I'm a newcomer to machine learning and currently diving into supervised learning methods. I've already grasped the theoretical basics of classification tasks and have just started exploring regression....
SuperciliousMe's user avatar
0 votes
0 answers
12 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
0 answers
6 views

The best order for analysis steps in building econometric model with time series linear regression

I am working on a project whose goal is to build a linear regression model for a time series dataset. I was provided with a blueprint of all required analysis steps. This led me to wonder what is the ...
Brzoskwinia's user avatar
0 votes
0 answers
14 views

How to combine a classificiation dataset with a pair-wise comparison dataset

Let's say I'm trying to train a neural network that predicts a single output [0.0, 1.0] value that correlates to photo realism which I can use either in a classification setting or for ranking. I have ...
ahbutfore's user avatar
  • 191
0 votes
0 answers
57 views

How to prune my Yolov8 object detection model?

I trained a yolov8-medium object detection model, but I'm not sure how to apply pruning on it. What is the proper way to prune it? I got this example code, but it only looks for ...
Mary H's user avatar
  • 1
-1 votes
0 answers
14 views

Which statistical analysis method to use, and what would be the outcomes

I have an assignment to do, no calculations needed but would need to decide what to use and how I would run it. Data from 2 questions: "Select up three personality traits that you would find most ...
Peter's user avatar
  • 1
1 vote
1 answer
18 views

Change of data shape when using IterativeImputer from sklearn

I am using the IterativeImputer from sklearn and I notice that it changes the data shape. Initially I have an (X,5) array where all columns except for the last one contain the missing value (which has ...
gmaravel's user avatar
  • 111
0 votes
0 answers
7 views

PAC-Learning, error estimation

I'm looking at this true/false question (currently in a ML course) and there's no given solution/explanation for this, I cant really understand what am I supposed to look for when facing this: "...
Aishgadol's user avatar
  • 111
2 votes
0 answers
23 views

Why is it called 'Test' dataset and not 'Testing' Dataset?

Training data is named as such as it is used for 'training'. Then why not the same for 'Testing' dataset? I apologise if this is not very relevant, but its something I believe only the community can ...
Sameervdtc's user avatar
0 votes
0 answers
12 views

How to classify/recognize postage stamp varieties?

As a hobbiest stamp collector, I often run into the need for classifying stamps based on minute differences, such as these: Now, I literally have thousands of them (in ziploc bags) and I am planning ...
René Becker's user avatar
0 votes
1 answer
25 views

How to interpret annotation data?

I am new to datasets. I have got an annotations train.json for MR image data like this - I want to train a Yolo-V8 model using this MR data images extracted from dicom raw data and annotations for ...
mrin9san's user avatar
  • 168
0 votes
0 answers
14 views

RFECV with Random Stratified K-Folds returns different features everytime

I am trying to learn more about Feature Selection in machine learning. I am working on a dataset that contains 17 features, and I have achieved about 75% accuracy on a Random Forest model with no ...
rehanqb's user avatar
0 votes
1 answer
26 views

Why torch activation functions contains parameters?

What is the purpose of the weights?
Тима 's user avatar
0 votes
0 answers
9 views

Can we calculate Bayes Error rate, if we have a simulated data?

I am going through ISL(Python) and in section 2.2.3 ( Page No. 36), the author writes, "For our simulated data, the Bayes error is 0.133. It is greater than zero, because the classes overlap in ...
Prashant Kumar's user avatar
0 votes
0 answers
15 views

how to eal with a column name having comma space or and

I am taking the Coursera assignments on SQL and came across to a question where one of the tables has a column with this name: Elementary, Middle, or High School I do not know how to deal with this ...
Baghban's user avatar
  • 101
0 votes
0 answers
75 views

How can I apply a technique from "ZHOU, Pei, et al. Self-Discover: Large Language Models Self-Compose Reasoning Structures. 2024" to my toy project?

I want to practice a technique from "ZHOU, Pei, et al. Self-Discover: Large Language Models Self-Compose Reasoning Structures. arXiv preprint arXiv:2402.03620, 2024." The article call it &...
Jaewoo Kim's user avatar
0 votes
0 answers
29 views

Why do seaborn.histplot and pyplot.hist generate two different histograms on the same data?

I'm trying to visualize a customer data, two of the variables I'm looking at are verified_status and video_transcription_length. ...
user161913's user avatar
0 votes
0 answers
20 views

Using Reinforcement learning for minimisation

I would like to use reinforcement learning for the optimisation of a given function under some contraints. Take for example the following problems: ...
Ach Raf's user avatar
0 votes
1 answer
18 views

How do I ensure final output shape matches input shape for a semantic segmentation task?

I trying to replicate the semantic segmentation example https://keras.io/examples/vision/oxford_pets_image_segmentation/ but train on my own data. I have 8 labels (7 features + background). My images ...
utx7563yu's user avatar
0 votes
0 answers
20 views

How to calculate rolling standard deviation in 1 hour intervals across dates?

I have time series data of electricity consumption. I want to calculate rolling standard deviation of 1 hour intervals with window size of 10 i.e. I want to take values from 8-9AM for last 10 days and ...
Yogesh's user avatar
  • 101
0 votes
1 answer
39 views

LSTM predicted negative values although the training data are all postive values

I am training LSTM to predict tree sap flow (30 min interval). I am keeping getting negative predictions, although the most of the predictions look good. I tried to use different scalers for ...
Jiaj's user avatar
  • 1
0 votes
1 answer
14 views

Understanding batching in pytorch models

I have following model which forms one of the step in my overall model pipeline: ...
Mahesha999's user avatar
0 votes
1 answer
17 views

Pytorch backward error

Here I overcame a problem about backward, below is a simple example written by python code. the print information is that This really confused me as self.weights is used as a important part in my ...
Ecthelion's user avatar
0 votes
0 answers
18 views

Calculate AUC-ROC and AUC-PRC for an LSTM Model

I have the following simple Bidirectional LSTM model for a binary classification task: ...
thatsroughbuddy's user avatar
0 votes
0 answers
9 views

SAS Macro: dereferencing a macro variable in the name of a column name of a dataset

In SAS dereferencing this does not work: ...
babipsylon's user avatar

15 30 50 per page