Skip to main content

All Questions

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

Hallucinations after fine tuning data augmentated dataset even with low loss

I tried to fine tuning using this dataset: https://huggingface.co/datasets/celsowm/enunciados_pge_rj_orpo created using some techniques of data augumentation using as source this simples page: https://...
celsowm's user avatar
  • 101
0 votes
1 answer
32 views

Is it possible to achieve both detection and image classification by training the model on the custom dataset?

I am beginning to work on a non-linear navigation system for educational videos as a part of my undergrad coursework project. As a part of it, I need to classify the unique frames (frame which is ...
keerthana s's user avatar
2 votes
0 answers
29 views

How to analyze furniture for digital reconstruction?

My end-goal is to take a single photo of a piece of common furniture (couch, chair, table) and create a 3d model from that. I'm a novice with deep learning as I've only done basic CNN's and such with ...
Jacksonkr's user avatar
  • 119
0 votes
1 answer
47 views

How to re-train ML model

I'm somewhat new to machine learning so there is one thing that I wanted to clarify. I was playing around with AWS Sagemaker, trained a model with some labeled data, deployed it to endpoint and set up ...
mangusta's user avatar
  • 103
1 vote
1 answer
47 views

Where am I going wrong in my CNN approach to automate cropping images?

I have a dataset compiled of geological images. They often have unnecessary padding to the left, right, and bottom. I also have a folder containing cropped versions of these images where the padding ...
Vulcan's user avatar
  • 11
2 votes
1 answer
37 views

Labeling policy for airplane detecting YOLO

I am training my YOLO to detect airplanes and drones. in some of the pictures it is impossible to detect that the object is indeed an airplane, and it even looks like a drone (pictures are taken from ...
Or Perez's user avatar
1 vote
0 answers
29 views

Any tutorials/courses to learn variational autoencoders on tabular data?

I aim to use variational autoencoders (VAE) to find interpretable latent spaces for genetic data. So, I need to understand how they work, what activation function to use, etc. But all tutorials and ...
Yulia Kentieva's user avatar
1 vote
2 answers
55 views

Deep Learning training strategy: Avoid shuffling individual training images, instead shuffle batches?

I am training a YOLO (You only look once) object detector for an application within an industrial environment. Since a fixed setup of cameras is used, the backgrounds of the images are camera-...
beinando's user avatar
  • 141
0 votes
0 answers
57 views

Downsides of training a neural network in constant time

Assumption Let's assume we collect a high quality amount of training data for machine translation for example parallel corpus data from the european parlament combined with other data. We store these ...
user1232048's user avatar
0 votes
0 answers
13 views

How can I augment a 1D tablar dataset using an additional 2D dataset?

I have the following two types of datasets: The dataset-1 is a tabular data that describe 7000 proteins. dataset-1 is only one file. dataset-2 consists of 7000 individual data files that are 2D ...
user366312's user avatar
0 votes
1 answer
48 views

Size of Dataset object [closed]

I defined a dataset as below ...
COTHE's user avatar
  • 13
1 vote
1 answer
63 views

Can you claim copyright over a social media post that is used to train an AI model?

Can user-generated content from social media platforms be considered copyrighted training data for AI models, despite agreements between the platforms and AI companies (note that the users themselves ...
Bharati Challa's user avatar
0 votes
1 answer
38 views

Reference request: data efficiency of LLM pre-training

I've seen it stated multiple times that LLMs have much worse data efficiency than humans (IE require more data to reach same or worse performance), EG this Tweet by Yann LeCun, or 19:30 in this talk ...
Jake Levi's user avatar
  • 101
2 votes
1 answer
147 views

How does Training and Validating work with Graph CNNs

I'm training a Graph Convolutional Neural Network to output embeddings for nodes that I eventually want to perform classification on. I am a little confused on how the training, validation, and ...
Kiran Manicka's user avatar
0 votes
0 answers
20 views

Predict outputs based on a variable subset of inputs

To simplify this: I have 5 columns in my dataset -> A, B, C, D and E. I want the neural network to predict the rest of the outputs based on a subset of inputs. For example: Case #1 Inputs -> (A) ...
Sam's user avatar
  • 1
0 votes
0 answers
86 views

Does DPO update the weights in the same way that LORA/Fine-Tuining does?

I've been working on making a conversational customer service fine-tune for the past couple months and now I am looking to improve its failure recovery. For example, If the agent makes a mistake, how ...
the-test-set-is-all-you-need's user avatar
0 votes
0 answers
32 views

Chat with your DB: How to get AI to follow your rules?

Context/Background: I have a single table in MySQL with info on 'members', including things like location, favourite types of music, favourite camping spots, etc. Required Behaviour: I need the system ...
Blue Da Noob's user avatar
2 votes
1 answer
218 views

Human trainers: collect data by 2-alternative force choice (2AFC)

To collect human intelligence data, we intend to use 2-alternative force choice (2AFC). A sample human intelligence task (HIT) is shown below. Can it be considered a 2AFC? Is such a HIT considered ...
Megidd's user avatar
  • 141
0 votes
2 answers
66 views

Can too much trainingdata have a negative impact?

I have to detect objects in an image. I want to use a neural network for this (yolov8). Since my objects are stacked, most of them are partially hidden and only front and side is visible. My dataset ...
Ef Ge's user avatar
  • 113
1 vote
0 answers
64 views

Largest fully open source LLMs including training

It seems that most of the open-sourced large language models (LLMs) like Llama 2 had the model released but not the exact training procedure and training data-sources (exact data revisions) so that ...
Kozuch's user avatar
  • 281
0 votes
1 answer
210 views

XML Input to assist in composing muusic

First time submitter here. I'm a composer of (for want of a better term) contemporary classical music - and I would like to use AI to improve my productivity. The specific issue I'm dealing with is ...
E Heilner's user avatar
3 votes
1 answer
682 views

Why are some LLMs trained on both CommonCrawl and Wikipedia/StackExchange?

Some LLMs are trained on both CommonCrawl and Wikipedia/StackExchange. Why? Does CommonCrawl already contain Wikipedia/StackExchange? E.g., from the LLaMa 1 paper: and from https://huggingface.co/...
Franck Dernoncourt's user avatar
0 votes
1 answer
63 views

How to label missing/default values for a named entity recognition dataset

I am building the training dataset for a named entity recognition model, with 2 tags: Name and Category and I am using a pre-...
mrang's user avatar
  • 3
2 votes
1 answer
837 views

What causes my loss curve to consistently oscillate when training an LLM?

Why is my loss curve consistently oscillating? Every 50 steps it jumps back up. I'm assumming there's a bug in my data, since I'm using this colab notebook that shows a proper train/loss at the bottom....
bmatzelle's user avatar
1 vote
0 answers
44 views

Is there a neural network architecture specialized for mapping lower-to-higher-dimensional data?

I am building a neural network that takes in a set of 86 parameters (primarily architecture-related, such as building floor area, kitchen size, number of a certain type of furniture, etc.) and outputs ...
JS4137's user avatar
  • 143
-1 votes
1 answer
78 views

Open access Adept-like dataset? (LLM-to-computer-input) [closed]

Here's a demo for Adept ACT-1 for Transformers. I don't doubt that one could create a demo video using zero-shot; actually I tested just now and the basic chat.openai.com interface was able to do some ...
llllvvuu's user avatar
  • 208
2 votes
1 answer
422 views

What's the architecture and size of neural-network-based reward models as used in reinforcement learning by human feedback

My rough understanding of RLHF as used for ChatGPT in a nutshell is this: A reward model is trained using comparisons of different responses to the same prompt. Human trainers rank these responses ...
Hans-Peter Stricker's user avatar
2 votes
2 answers
98 views

Is there a measure of model complexity?

Is there a measure of model complexity?
Justaperson's user avatar
0 votes
1 answer
57 views

AI and Machine Learning Prediction Algorithms for predicting outcome results of Hypothetical poll

Can artificial intelligence and Machine Learning Prediction Algorithms assist in deciding the Outome Results of a Hypothetical Online Poll? Poll: Selecting favorite American President till date. ...
Prashant Akerkar's user avatar
0 votes
0 answers
31 views

Longer DNN training times when using evolutionary algorithms

I am comparing my deep neural network (DNN) performance when using 2 types of optimizers: gradient-based Adam (properly tuned) and a population-based optimization algorithm (e.g., genetic algorithm (...
knowledge_seeker's user avatar
1 vote
1 answer
139 views

Creating a Dataset from Time Series Data

Context I'd like to build a regression model for this data to predict a user's test scores given their study habits. Basically, the variables are in two separate csv tables similar to the ones below. ...
LittleLulatsch's user avatar
0 votes
1 answer
95 views

What papers can I read that explore model performance vs dataset size?

I am trying to estimate how many images I need to label for an object detection task. I understand a lot of variables are at play, but I'd like to find some papers that have already explored this ...
Alexis Winters's user avatar
0 votes
0 answers
316 views

When would you use prompting vs. fine tuning?

I would like to hear your thoughts on when is it appropriate to use prompting vs. fine-tuning. Does one make more sense for specific tasks than the other. Kindly elaborate.
Josiah Cheruiyot's user avatar
0 votes
2 answers
176 views

Why does linearly decreasing batch sizes result in exponentially increasing training times?

I'm quite new to machine learning and wanted to ask a question regarding why reducing batch sizes cause exponentially increasing training times. An example of this relationship between batch size and ...
Alpy's user avatar
  • 3
6 votes
1 answer
2k views

How was ChatGPT trained?

I know that large language models like GPT-3 are trained simply to continue pieces of text that have been scraped from the web. But how was ChatGPT trained, which, while also having a good ...
HelloGoodbye's user avatar
9 votes
1 answer
2k views

What causes ChatGPT to generate responses that refer to itself as a bot or LM?

ChatGPT occasionally generates responses to prompts that refer to itself as a "bot" or "language model." For instance, when given a certain input (the first paragraph of this ...
Obie 2.0's user avatar
  • 192
1 vote
0 answers
374 views

Is it possible to create an AI that produces output without giving it input?

AFAIK an AI is first trained using a data set of input and output values. After the training proccess you can give the AI input and it will produce output. For example when you write a sentence to an ...
zomega's user avatar
  • 119
1 vote
1 answer
3k views

Fine-tune GPT-Neo with prompt and completion?

I'm new to AI and machine learning. To fine-tune GPT-3, I understand that we need a set of training examples that each consist of a single input ("prompt") and its associated output ("...
SoftTimur's user avatar
  • 111
1 vote
0 answers
37 views

bad prediction when having noise on the data: LSTM time-series regression

I want to predict the force plate using a smart insole using the LSTM model for time series prediction. the data on the force plate has positive and negative values (I think the resulting positive ...
stack offer's user avatar
3 votes
4 answers
2k views

How is MNIST only providing the training and the test sets? What about the validation?

I was taught that, usually, a dataset has to be divided into three parts: Training set - for learning purposes Validation set - for picking the model which minimize the loss on this set Test test - ...
tail's user avatar
  • 167
1 vote
1 answer
449 views

Batching together similar length sequences to avoid padding and packing

I am training an RNN in PyTorch to produce captions for images. It's a pretty standard architecture – the image is processed by a pre-trained InceptionV3 to extract features, the recurrent module ...
czypsu's user avatar
  • 111
0 votes
1 answer
37 views

What kind of neural network and GPU should I use to classify images into > 10 000 classes?

I am trying to developp an image classifier that would have more than 10 000 classes but I don't know what kind of neural network I should use ? Some Other questions arise from this one : How big ...
Louis Delporte's user avatar
0 votes
0 answers
43 views

Is the neural network 100% accurate on training data if epoch loss is minimized to 0?

This seems like a silly, trivial question, but I just want to confirm it in case I'm missing something. I'm trying to train a ReLU neural network, which is supposed to be a function that satisfies ...
Acad's user avatar
  • 111
0 votes
1 answer
116 views

Storing training dataset in a platform like mlflow

I am pretty new to Machine learning and would like to know whether there are experiment management platforms that also allow storing and managing training datasets (images, in my case). I am familiar ...
Igor's user avatar
  • 303
1 vote
1 answer
101 views

Datasets input at model.fit produce unexpected results of training loss vs validation loss

Im trying to train a neural network (VAE) using tensorflow and Im getting different results based on the type of input in the model.fit. When I input arrays I get normal difference between the ...
user avatar
1 vote
0 answers
14 views

how to manage the impact of Covid on building a machine learning model

I need your suggestions for using historical data to build a machine learning model for analyzing the market and build an AI model(tree based model/random forest or regression analysis) for setting ...
Mahsa's user avatar
  • 111
1 vote
1 answer
252 views

Should I include overlapping (input) Data in my training data

If I have time dependent data and want to predict the relative change for a future time. Should I separate the data so that the input times don't overlap? With an example: I have hourly temperature ...
KarlTheGreat's user avatar
0 votes
0 answers
67 views

How to use oxford5k for training?

Generally, we have training data with landmark IDs, their GTs (positive samples), and then separate query images and corresponding positive samples for evaluation. In the Oxford5k or ROxford5k, one ...
David's user avatar
  • 111
1 vote
0 answers
74 views

Why does the SVM perform poorly on test data that has a different class distribution than the training data?

Do you know why the SVM performs poorly on test data that has a different class distribution than the training data? The training data has around 15 classes, and the additional testing data has around ...
Allie's user avatar
  • 11
0 votes
1 answer
57 views

How to create a dataset for binary classification

I would like to classify whether a pot of water is boiling or not using a CNN. Is it enough to take pictures of boiling water using only one pot, or should I use different pots for this to generalize ...
Joel Castro's user avatar