Questions tagged [training]

For questions about training networks, rules systems, or other AI system components.

Filter by
Sorted by
Tagged with
0 votes
1 answer
6 views

Is there a way to not change some weights during training of PyTorch model?

Is there a way to let some chosen weights not change during the training step in PyTorch framework? By chosen I mean for example delivering suitable arrays, with shapes exactly like layer's arrays ...
user avatar
  • 1,029
0 votes
0 answers
26 views

How to create an AI that chats like me? [closed]

I have been researching how to make this possible using GPT-2 and a data source from my chats. But is there a way to train AI the same way Replika does? Train the AI in Live mode based on my answers ...
user avatar
  • 1
0 votes
0 answers
24 views

Training a GAN after after evaluation metric reaches minimum

I am training a StyleGAN-3 using one of the pre-trained models. At some point, roughly halfway through the 5000 kimg recommended for fine-tuning, the FID50K score starts oscillating around a minimum ...
user avatar
  • 1
0 votes
0 answers
33 views

How to explain near zero gradients on first epochs?

As I understand the gradient should reflect how near the weights are to the optimal values. In this way i will expect that on the first epochs the gradients far from zero or at least not mostly zero ...
user avatar
0 votes
0 answers
43 views

What is your training time of Resnet-18/Resnet-50 on Imagenet?

My training of Resnet-18 network on Imagenet using Tesla V100 seems to be quite slow (1 epoch is about 2,5 hours, batch 128). Increasing the number of GPUs does not seem to help. What is your training ...
user avatar
  • 121
1 vote
1 answer
118 views

What is the reason we loop over epochs when training a neural network?

After reading through this thread and some other resources online, I still do not understand the role of epochs in training a neural network. I understand that one epoch is one iteration through the ...
user avatar
0 votes
0 answers
45 views

Does the transformer model have any inherent ordering?

I'm aware of the practice of positional encoding, which inserts information to convey the relative positions of input data points. Unfortunately, I do not have a great grasp of the transformer model ...
user avatar
2 votes
1 answer
40 views

Is there a way to inject linear constrains during GAN training?

Given that I'm training a generative model, (say a generative adversarial network), and I know that my (real) inputs (let's say vectors $\textbf{x} \in \mathbb{R}^n$) satisfy linear constraints of the ...
user avatar
2 votes
2 answers
96 views

How to deal with changing environment in reinforcement learning

I am new to RL and I'm currently working on implementing a DQN and DDPG agent for a 2D car parking environment. I want to train my agent so that it can successfully traverse the env and park in the ...
user avatar
0 votes
0 answers
19 views

Arabic words are reversed when I call lstmeval while training in tesseract

I've been trying to train for a new font using Tesseract. It has worked with the default data. But I wanted to train the model for my own generated data which is close to the data that I wanted to use ...
user avatar
1 vote
1 answer
48 views

What will happen if I concatenate one-hot-encoded categorical features along with continuous numerical features?

Here is one row from my data: H 7.042 5.781 5.399 -9.118 5.488 7.470 The first column is a categorical class. The rest of them are continuous numerical ...
user avatar
1 vote
0 answers
27 views

Detecting cheats visually using AI

I really like to play my favorite 3D shooter game online. Unfortunately, it is really old and cheat protection isn't really common there, but cheaters are! It is very frustrating, because it really ...
user avatar
  • 11
1 vote
1 answer
52 views

Do neural networks, trained with backpropagation algorithm, exploit the concept of synaptic plasticity?

Is there some of Hebb's rule behind the concept of backpropagation learning rule of a simple supervised neural network, that for example is trained for classification task ? I was reading about the ...
user avatar
0 votes
0 answers
13 views

Yolo objectness parameter (called p0) vs probability parameters as explained by Joseph Redmon

I have been watching Joseph Redmon (developer of YOLOv3) lecture about YOLO from 45:04 where he explains why he needs both predictions: "objectness" called P0 VS class probabilities called ...
user avatar
  • 131
0 votes
1 answer
36 views

What techniques exist to increase the learning importance of difficult-to-learn labels over easy ones?

I am training a model to place labels in image data. Some labels are learnt very quickly by the model while others take a long time to perfect. I cannot simply add more labeled data with only the ...
user avatar
0 votes
0 answers
27 views

Test accuracy go down after decreasing learning rate

My project include classification of images into several classes. I'm having a strange issue related to adding mixup augmentation. The accuracy of the training set and the validation set keep rising ...
user avatar
  • 171
1 vote
1 answer
55 views

Why doesn't dropout mislead results during evaluation?

I have seen that, usually, the dropout layer is used differently in training and evaluation modes, i.e. it is recommended to use during training but not in evaluation/testing. Dropout does remove a ...
user avatar
  • 13
0 votes
1 answer
80 views

Weights initialization once the Neural Network is trained

I am trying to understand how weights are initialized in a Neural Network using Keras deep learning framework and what happens if I train a Neural Network and then I want to train it again: are the ...
user avatar
0 votes
0 answers
37 views

Impact of imbalanced dataset on CNN model performance

I trained a 1D CNN model to model bacterial plate count based on time series data of water temperature. Bacterial place count is numerical, based on which I created two category variables, namely &...
user avatar
1 vote
0 answers
37 views

Which machine learning algorithm can be used to identify patterns in a large file of numbers?

I'm new to machine learning and have many questions, but today I want to know if my case can be solved by machine learning, and if the answer is yes, I would like to know what to learn first and which ...
user avatar
0 votes
1 answer
55 views

Is there a way to use AI to compare thousands of files and detect the ones containing "unusual" content?

Is there a way to use python and AI to compare thousands of files and detect the ones containing "unusual" content? Those files are supposed to have "homogeneous" configuration ...
user avatar
  • 109
0 votes
0 answers
18 views

How to train with a non-differentiable activation function (such as SVT in deep unrolling low-rank optimization)?

I planned to design a deep unfolding for decomposition into low-rank and sparse in Pytorch environment. I read this paper that might help me to understand how to do it. I always taught that this model ...
user avatar
0 votes
0 answers
29 views

How to train a FCNN with audio spectrogram images?

I'm working on an audio dereverberation deep learning model, based on the U-net architecture. The idea of my project came from image denoising with autoencoders. I feed the reverberated spectrogram to ...
user avatar
0 votes
0 answers
36 views

Transfer learning on YOLOv5 for character and shape detection

The task is to detect rotated alphanumeric characters embedded on colored shapes. We will have an aerial view of the object (from a UAS: Unarmed Aerial System), something of this sort: (One Uppercase ...
user avatar
  • 121
0 votes
0 answers
14 views

What to infer If a parameter value is the same as I initialized while training?

I am running a neural network model. There are several parameters. I initialized a new parameter to a value (say k). When I observe its change during the training, it is not changing like other ...
user avatar
  • 2,989
1 vote
1 answer
162 views

What is a policy training target in AlphaZero?

In AlphaZero's attached pseudocode, they create a training target for the policy network in this way. ...
user avatar
  • 159
4 votes
1 answer
358 views

Do we use validation and test sets for training a reinforcement learning agent?

I am pretty new to reinforcement learning and was working with some code for the PPO and DQN algorithms. After looking at the code, I noticed that the authors did not include any code to setup a ...
user avatar
  • 187
4 votes
2 answers
98 views

Can I apply reparametrization trick on "any" deep neural network?

I came across the "reparametrization trick" for the first time in the following paragraph from the chapter named Vector Calculus from the test book titled Mathematics for Machine Learning ...
user avatar
  • 2,989
2 votes
0 answers
31 views

How to fix high variance of the returns on a 2d env?

I'm trying to train an agent on a self-written 2d env, and it just doesn't converge to the solution. It is basically a 2d game where you have to move a small circle around the screen and try to avoid ...
user avatar
0 votes
1 answer
54 views

How do Tensorflow models and YOLO differ in terms of training steps?

Can anybody explain how the training steps work for the Tensorflow Object Detection algorithms available on the Tensorflow 2 Detection Model Zoo? For instance, YOLOv5 cycles through epochs. As I ...
user avatar
  • 119
1 vote
0 answers
10 views

References for the convergence of gradient-based algorithms for training neural networks

I'm looking for some good references that give convergence results of training neural networks. I'm decently familiar with works that analyze the convergence of SGD, and, in particular, I really like ...
user avatar
  • 746
5 votes
1 answer
265 views

How to decide a train-test split?

In almost every ML model, a train-test (or train-test-val split) is critical to assess the model's performance. However, I have always wondered what the rationale is to decide a particular train-test ...
user avatar
1 vote
0 answers
23 views

Should I train a neural network with data with or without a constraint?

I want to train a Neural Network (NN) using a dataset. I want to use the NN model as a prediction function in one algorithm. However, in the algorithm, any data that does not meet a specific ...
user avatar
0 votes
1 answer
37 views

Does the ANN's training data include the proper output for every neuron?

I was designing an Artificial Neural Network a while back, but hit a bump when I got to the backpropagation. I was having trouble making the script choose whether to add or subtract from the weights, ...
user avatar
0 votes
0 answers
17 views

What is the difference between supervised and unsupervised training in T5?

I know unsupervised training for T5 is like: input: He went X output: X to school Z is this equivalent to the following in a supervised manner: ...
user avatar
  • 101
-1 votes
1 answer
31 views

What practically makes a good architecture of ANN?

When we take a look at the literature there are so many opinions. I was wondering what are some generally good practices to design an architecture, like how much depth would you prefer and how much ...
user avatar
0 votes
0 answers
26 views

How to assess the goodness of a text generation algorithm

Take a RNN network fed with Shakespeare and generating Shakespeare-like text. Once a model seems mathematically fine, as can be assessed by observing its loss and accuracy over training epochs, how ...
user avatar
  • 101
8 votes
3 answers
808 views

Is it okay to use publicly available Instagram videos to train an AI?

Since I haven't found any good training data for my university project, I want to use pictures and videos from public Instagram profiles. Am I allowed to do that?
user avatar
2 votes
1 answer
79 views

What problem does the neural network really solve?

In the image below taken from a Youtube video, the author explains that the neural network can be used to fit a relational graph for a set of data points shown by the green line. And that this is ...
user avatar
0 votes
0 answers
36 views

What's the benefit for using a Kalman filter for training a neural network compared to other optimization algorithms?

I found a paper about using an Unscented Kalman Filter(UKF) for traning a neural network. The UKF filter is modified so it works for parameter estimation. Assume that we have a neural network model $\...
user avatar
  • 143
0 votes
1 answer
46 views

Validation accuracy less than training accuracy (with no sigh of overtraining)

I am working with a deep CNN with over 100k sample data. I divided it up into 75% training, 12.5% validation and 12.5% for testing. As I train my network, the training accuracy approaches near 100% ...
user avatar
1 vote
1 answer
331 views

Tensorflow object detection model total loss starts out good, but suddenly explodes up to high loss numbers

I'm training a Tensorflow object detection model with approx. 7500 images of two classes, which contains approx. 10,000 classes per class. I'm using Tensorflow 2.6.0, in case that is relavent. I am ...
user avatar
  • 119
0 votes
0 answers
38 views

How big should the dataset for retraining ssd_mobilenet_v2 be?

I have retrained ssd_mobilenet_v2 using my own dataset with 2 classes (pen or pencil), using object detection API. For my project, I expect users to select specific pencils from all pencils and ...
user avatar
  • 1
1 vote
1 answer
33 views

Using Human Confirmation in place of a loss Function for Training

Has there been any experimentation in designing an AI to prompt a human to judge the accuracy of it's outcomes? instead of using a loss function, a human can judge the accuracy of it's estimation ...
user avatar
  • 323
0 votes
0 answers
24 views

Adding data to training results in loss random peaks

I have succesfully trained ssd_mobilenet_v2_keras for object detection, with a dataset of about 3700 images. Now I have more images to add. I tried adding only a few images (150-300) to see what ...
user avatar
  • 73
2 votes
1 answer
104 views

Is there any way to train a neural network without using gradients?

The only algorithm I know for updation of weights of a neural network is based on gradients. The update equation can be roughly written as $$w \leftarrow w - \nabla_{w}L$$ where $\nabla_{w}L$ is the ...
user avatar
  • 2,989
-1 votes
1 answer
49 views

How to re-training an AI model to have smaller input image size

I need a PyTorch Model which can do road segmentation on OAK-D camera. The model provided requires Input Image Size: 896*512, which is too big for running on OAK-D camera. Thus I need to re-training ...
user avatar
  • 181
0 votes
0 answers
12 views

What is meant by non-convergent limit cycles?

Limit cycle is a closed curve that is isolated i.e., no other closed curve near to it. You can read the following paragraph from here If there is (such) a closed curve, the nearby trajectories must ...
user avatar
  • 2,989
1 vote
0 answers
42 views

Is stability an attribute of model or training algorithm used or combination of both?

From this answer, stability is attributed to a learning algorithm A stable learning algorithm is one for which the prediction does not change much when the training data is modified slightly. At ...
user avatar
  • 2,989
0 votes
0 answers
15 views

Weight for Samples on SVM (Support Vector Machine)

There is a option sample_weight in fit(X[, y, sample_weight]) function (OneClassSVM, sklearn library). If I use the option ...
user avatar

1
2 3 4 5
8