Questions tagged [training]

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

Filter by
Sorted by
Tagged with
1
vote
0answers
23 views

Identifying rotating and resizing letters with background noise

I'm trying to complete a certain type of captcha for academic purposes. Here is what it looks like: Between captchas the calligraphy of the letters is the same, but the letters may be resized and ...
0
votes
0answers
15 views

Train a model for different scenario and gather performance results in a single place

Recently, I extend a master's thesis. I am now in a training phase for the model associated with it. I have access to many node GPUs. I would like to train this model on different scenarios, e.g. ...
0
votes
1answer
53 views

Is it possible to overfit a model on infinite amounts of data?

This is a theoretical question. Is it possible to overfit a model on infinite amounts of data? Let me clarify there are no duplicates. Say, we have a generator function that produces data, with the ...
0
votes
0answers
15 views

Problems while transforming a 2D Variational Autoencoder into a 1D Version

I am trying to addapt the Keras variational autoencoder (VAE) here from a 2-D input/output (matrix of a picture) to a 1-D input/output (just a vector). I thought this would be a fearly easy task, but ...
1
vote
1answer
24 views

What is meant by “stable training” of a deep learning model?

I have read it said that the "stable training" of a deep learning model is important. What is meant by "stable training" of a deep learning model?
0
votes
0answers
10 views

How exactly is masking performed in the training part of the paper “Semi-Supervised Classification with Graph Convolutional Networks”?

I am struggling to understand the training part of the paper Semi-Supervised Classification with Graph Convolutional Networks (2017) by Thomas Kipf and Max Welling. The GitHub repo is here. I do not ...
1
vote
0answers
14 views

Necessity of likelihood in training energy-based models

Lately, I've been getting into energy-based models (EBMs) through some of Yann LeCun's recent talks, where he advocates the use of non-normalized models because it allows for more flexibility in the ...
0
votes
1answer
15 views

A neural network to learn the connection between two totally different type of images

I have a dataset of two different type of images. Say, I have images of a person and his all 10 fingerprints. I want to create a relation between them to predict one from another. How I can do that ...
0
votes
2answers
52 views

What is the process working on Tensorflow model.fit()? [closed]

I created a binary image classification model. The dataset contains about 500K images in each class, with ratio = Train : Validation : Test = 7 : 2 : 1. Total images = 1M I split my dataset into 5 ...
2
votes
1answer
30 views

Is it possible to design an AI with two inputs and a Boolean output?

I am having a difficult time explaining to my boss that what he is trying to achieve may not be possible or within reason. We have a database of 3 Million data points per computer across hundreds of ...
1
vote
0answers
15 views

Why does Adam optimizer work slower than Adagrad, Adadelta, and SGD for Neural Collaborative Filtering (NCF)?

I've been working on Neural Collaborative Filtering (NCF) recently to build a recommender system using Tensorflow Recommenders. Doing some hyperparameter tuning with different optimizers available in ...
0
votes
0answers
9 views

Choosing the size of the network for Neural Collaborative Filtering (NCF)?

I've been working on Neural Collaborative Filtering (NCF) recently to build a recommender system. After doing some hyperparameter tuning with various sizes for embedding and dense layers sizes, from ...
0
votes
0answers
5 views

If training a network to predict signal phase, should you use wrapped or unwrapped phase as the target data

I'm developing a network that will predict direction on the unit circle and I also want to predict the phase of each frequency bin at each time step. Would it better to train the network on wrapped or ...
0
votes
0answers
31 views

How to train feedforward network to recognize images?

Context I'm trying to create network for digits recognition. All digits are the same font and size of 40x40. I know that I can use feedforward network or CNN. I'd like to use the first one. Issue I ...
0
votes
0answers
17 views

Comparison between TD(0) and MC ( or GAE )?

I'm getting started with DRL and have trouble distinguishing TD(0), MC, and GAE; and which scenarios one's better than others. Here is what I understand so far: TD(0): increment learning, can learn ...
2
votes
1answer
45 views

How to properly use Flatten layer?

Context I'm trying to create net that will be able to recognize printed-like digits. Something like MNIST, but only for standard printing font. Images are of the size 40x40 and I'd like to put them ...
1
vote
1answer
22 views

Video Analysis: Providing a success score for a of a student carrying out a specific task

I have an AI/ML challenge in relation to video analysis and am unsure where to start. I am investigating an application that will grade students performance of carrying out a task, based on analysis ...
2
votes
1answer
32 views

How to handle class imbalancing when the actual data are that way

My supervised learning training data are obtained from actual data; and in real cases, there's one class which happens less often than other classes, just around 5% of all cases. To be precise, the ...
1
vote
1answer
34 views

How to source training data in ML for information security?

A company entrusts a Data Scientist with the mission of processing and valuing data for the research or treatment of events related to traces of computer attacks. I was wondering how would he get the ...
2
votes
1answer
111 views

Why is the Backpropagation algorithm used to train the Multilayer Perceptron?

I've read on the book NND by Martin Hagan et al (chapter 11), that to train the feed-forward neural network: Multilayer Perceptron one uses the Backpropagation algorithm. Why this algorithm? Could ...
0
votes
0answers
10 views

Predicting training time using randomly generated datasets

Given a dataset, I need to predict the amount of time it will take to fit a model to it. I plan to do this by creating a csv containing the logs of previously fit models, and passing that data itself ...
1
vote
1answer
39 views

How to properly resume training of deep Q-learning network?

I'm currently training a deep q-learning network. Due to resource limitations, I am not able to train the model to the desired performance in one go. So what I'm doing now is training the model for a ...
2
votes
0answers
19 views

How to add prior information when predicting using deep learning models?

Background I'm building a binary classification model for a pair match problem using CNN, e.g. whether person A1 likes product B1 or not. Model input features are sequence features of the person and ...
2
votes
1answer
57 views

How to recover the target Q network's weights solely from the snapshots of the primary Q network's weights in DQN?

Suppose that I have a DQN agent, which has two neural networks: one is the primary Q network and the other is the target Q network. In every update, the target Q network is updated with a soft update ...
1
vote
0answers
26 views

Why do you calculate the mean and standard deviation over the complete dataset before training rather than for every batch?

In most implementations of neural networks the features are scaled to make the optimization of the loss function as stable as possible. Mostly a min-max scaler is used. Alternatively, there is also a ...
1
vote
1answer
40 views

How to interpret this learning curve of my neural network?

How to interpret the following learning curves? Background: The accuracy starts at 50%, because the network has a binary output (0 or 1). I chose an exponentially decreasing learning rate of the ...
0
votes
0answers
15 views

Mixed precision training - why we're fine with doing point wise operations in FP32

I'm starting to learn more about mixed-precision training, and I'm in particular confused about point-wise operations. In the original article (link), the authors mention, citing: Point-wise ...
2
votes
1answer
93 views

What is a good convergence criterion for Q-learning in a stochastic environment?

I have a stochastic environment and I'm implementing a Q-table for the learning that happens on the environment. The code is shown below. In short, there are ten states (0, 1, 2,...,9), and three ...
3
votes
1answer
55 views

When using PCA for dimensionality reduction of the feature vectors to speed up learning, how do I know that I'm not letting the model overfit?

I'm following Andrew Ng's course for Machine Learning and I just don't quite understand the following. Using PCA to speed up learning Using PCA to reduce the number of features, thus lowering the ...
4
votes
1answer
251 views

Is it practical to train AlphaZero or MuZero (for indie games) on a personal computer?

Is it practical/affordable to train an AlphaZero/MuZero engine using a residential gaming PC, or would it take thousands of years of training for the AI to learn enough to challenge humans? I'm having ...
0
votes
0answers
35 views

Data Augmentation of store images using handwritten labels

I am new to AI and NN. I've started learning using Geron's book on Tensorflow. My first project ("Smart Shelf") is to determine which items in a store have been purchased and need refilled. ...
0
votes
1answer
28 views

Number Series Continuation? [closed]

I am new to AI. I have a series of numbers ranging from x to y and I have a lot of data to train with What I am trying to do is, let's say from 0 to 1, I train it with data calculated over time and ...
0
votes
0answers
10 views

Dividing datasets to reveal opposing signals

I have a set of data to train with comprising of 100 elements, 50 of which support theory A, and 50 support theory B. It turns out that both theories are valid, but the signal that A is valid is the ...
2
votes
0answers
32 views

Single-value loss/training in a CNN with a tensor output

I am playing around with an idea of using using Q-learning with a DQN (Deep Q-Network), to determine the optimal position of a number of 'units' on a grid of allowed locations, according to some ...
5
votes
2answers
65 views

Do AlphaZero/MuZero learn faster in terms of number of games played than humans?

I don't know much about AI and am just curious. From what I read, AlphaZero/MuZero outperform any human chess player after a few hours of training. I have no idea how many chess games a very talented ...
0
votes
1answer
76 views

How to train a policy model incrementally to solve a problem similar to the vehicle routing problem?

I have a problem similar to the vehicle routing problem (VRP) that I want to solve with reinforcement learning. In this problem, the agent starts from the point $(x_0, y_0)$, then it needs to travel ...
1
vote
0answers
12 views

How are the parameters $\alpha_i$ of hard attention trained?

I have a question about Show, Attend and Tell: Neural Image CaptionGeneration with Visual Attention paper by Xu. The basic mechanism of stochastic hard attention is that each pixel of the input image ...
2
votes
0answers
42 views

How to train/update neural networks faster without a decrease in performance?

I noticed that there are many studies in recent years on how to train/update neural networks faster/quicker with equal or better performance. I find the following methods(except the chips arms race): ...
0
votes
1answer
65 views

How to predict the best from a set of messages - best practice

Suppose I have a set of messages A,B,C,D and I want to produce the best message for a website user at a given time. For training I plan to show random users a random single message [A/B/C/D] and fill ...
2
votes
0answers
66 views

Offline/Batch Reinforcement Learning: when to stop training and what agent to select

Context: My team and I are working on a RL problem for a specific application. We have data collected from user interactions (states, actions, rewards, etc.). It is too costly for us to emulate agents....
0
votes
0answers
18 views

Neural Network trains towards 1 despite target

So I'm trying to make my first neural network and have just finished my back propagation functions. I got the algebra from brilliant and thought I'd understood it, but my bug proves otherwise. The bug ...
0
votes
2answers
28 views

Semantic segmentation CNN outputs all zeroes

I'm using MATLAB 2019, Linux, and UNet (a CNN specifically designed for semantic segmentation). I'm training the network to classify all pixels in an image as either cell or background to get ...
1
vote
0answers
39 views

Is training on single game each time appropriate for an agent to learn to play checkers

I was facing a problem I mentioned in a previous question but after a while, I realize that maybe the problem in the dataset not in the learning rate. I build the dataset from white positions only i.e ...
1
vote
0answers
25 views

The last target name is missed in the test set

I am training a neural network with a dataset that has 51 classes and 6766 data in it. I used 80% for the training set, 10% for validation, and 10% for the test. After training I got confusion matrix ...
1
vote
0answers
40 views

DDQN Agent in Othello (Reversi) game struggle to learn

This is my first question on this forum and I would like to welcome everyone. I am trying to implement DDQN Agent playing Othello (Reversi) game. I have tried multiple things but the agent which seems ...
1
vote
0answers
60 views

Is the performance of a neural network, which was trained with encrypted data and weights, affected if the weights are decrypted?

Suppose that a neural network is trained with encrypted (for example, with homomorphic encryption and, more precisely, with the Paillier partial scheme) data. Moreover, suppose that it is also trained ...
6
votes
1answer
108 views

During neural network training, can gradients leak sensitive information in case training data fed is encrypted (homomorphic)?

Some algorithms in the literature allow recovering the input data used to train a neural network. This is done using the gradients (updates) of weights, such as in Deep Leakage from Gradients (2019) ...
3
votes
0answers
58 views

Why is there a Uniform and Normal version of He / Xavier initialization in DL libraries?

Two of the most popular initialization schemes for neural network weights today are Xavier and He. Both methods propose random weight initialization with a variance dependent on the number of input ...
0
votes
0answers
38 views

Is there any rule of thumb to determine the amount of data needed to train a CNN

I am training an AlexNet Convolutional Neural Network to classify images in a dataset. I want to know if there is any general rule for using data augmentation in training a neural network. How can I ...
1
vote
1answer
63 views

Can someone explain me what does this loss curve says?

I was training a CNN model on TensorFlow. After a while I came back and saw this loss curve: The green curve is training loss and the gray one is validation loss. I know that before epoch 394 the ...

1
2 3 4 5
7