Stack Exchange Network

Stack Exchange network consists of 175 Q&A communities including Stack Overflow, the largest, most trusted online community for developers to learn, share their knowledge, and build their careers.

Visit Stack Exchange

Questions tagged [training]

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

2
votes
1answer
91 views

Understanding K-fold Cross Validation

I have a doubt regarding the cross validation approach and train-validation-test approach. I was told that I can split a dataset into 3 parts: Train: we train the model. Validation: we validate and ...
1
vote
1answer
25 views

Leave One Out Testing

I am currently working with a small dataset of 20x300. Since I have so few datapoints, I was wondering if I could use an approach similar to leave-one-out cross-validation but for testing. Here's ...
0
votes
0answers
18 views

I use the “same” dataset for validation and testing, but why I got different accuracy?

I am following the caffe cifar10 example (http://caffe.berkeleyvision.org/gathered/examples/cifar10.html). In this example, it uses cifar10 training and validation dataset from (http://www.cs.toronto....
0
votes
0answers
7 views

Can't create datasets and load images in COCO annotator

I'm trying to annotate images with COCO key points for pose estimation using https://github.com/jsbroks/coco-annotator. As described in the Installation section I cloned the repo. I installed Docker ...
1
vote
2answers
34 views

Divide classes into truncated and non-truncated objects

At the moment I am working on a vehicle counting & classification project. For a specific part in the project I need to get back only the completely visible vehicles from my input data (images). ...
1
vote
2answers
62 views

Drone training, how to train without training data?

I setupped a small drone simulator using PhysX, the time step is at 200 hz, while motors update like regular ESCs (at 50 Hz). I computed the inertia matrix, tweaked a bit mass of components to be real,...
2
votes
0answers
35 views

Difference between retraining on different portions of data and training initially on larger data set

I have a large data set that doesn't fit in memory and would have to use something like Keras's model.fit_generator if I would like to train the model on all of the ...
0
votes
1answer
30 views

Why could an overfitted CNN model have a higher validation accuracy?

I am currently training a CNN model by using cifar10 images (50000 for training, another 10000 for validation). I plot training loss, validation loss and accuracy against training iteration: I am ...
2
votes
1answer
21 views

Adding input features - is complete re-training required?

I've never worked with very large models that require weeks or months of training, but in such a situation, what happens if you want to add extra features inputs, do you need to re-train the entire ...
4
votes
2answers
132 views

Use Machine Learning/Artificial Intelligence to predict next number (n+1) in a given sequence of random increasing integers

The AI must predict the next number in a given sequence of incremental integers (with no obvious pattern) using Python but so far I don't get the intended result! I tried changing the learning rate ...
0
votes
0answers
11 views

Benefits in using multiple LSTM layers?

I am working on a time series forecasting problem and I am in the process of choosing the optimum network structure. Currently I have a 200 cell LSTM layer fully connected to 100 neurons in an ...
1
vote
1answer
17 views

Is it mostly the case to train with available models

I quite often find projects using pre-trained model and using them as a starting point for their new model that learns something novel from thier dataset or on-live learning process - e.g. using a ...
1
vote
1answer
26 views

how to benefit from previous training weights in training again to increase accuracy?

I have trained a modified VGG classification CNN, with random initialized weights; therefor the validation accuracy was not high enough for me to accept (around 66%). now using the weights resulted ...
3
votes
1answer
42 views

Why are not validation accuracy and loss as smooth as train accuracy and loss?

I am training a modified VGG16 network for classification (adding 0.5 dropout after each of the last FC layers). In the following plot I am training for a small number of epochs as an example, and it ...
0
votes
1answer
28 views

CNN output generally has more than one category in one-hot categorization?

I'm a bit of a CNN newbie, and I'm trying to train one to image classify pictures of pretty similar looking particles. I'm making the inputs and labels by hand from a set of 48x48 grayscale images, ...
2
votes
1answer
52 views

Can I calculate the training performance of GPUs by comparing their specification?

I am currently using Nvidia GTX1050 with 640 CUDA cores and 2GB GDDR5 for Deep Neural Network training. I want to buy a new GPU for training, but I am not sure how much performance improvement I can ...
0
votes
1answer
20 views

Why is a Nvidia Single Board computer less than ideal for AI model training?

Conventional NVIDIA GPUs, such as the Titan and or GT1080, are used to train AI models. Why would a Jetson Nano board be less than ideal as a substitute for a conventional GPU? CONTEXT I would like ...
1
vote
0answers
25 views

What methods are there to generate artificial training examples based on existing training examples?

I have a small dataset (117 training examples) and many features (4005). Each of the training examples is binary labeled (healthy / diseased). Each feature represents the connectivity between two ...
1
vote
1answer
19 views

What is the goal of the model and is the training data relevant to that?

The model that we develop in artificial intelligence.What is its purpose,and what training data is relevant to it.
2
votes
2answers
42 views

Export trained AI/ML model

From what I know, AI/ML uses a large amount of data to train an algorithm to solve problems. But since it’s an algorithm, I was wondering if it's possible to export it. If I trained an AI with R, ...
0
votes
0answers
15 views

Why validation performance is unstable for my LSTM based model (labelling problems)?

I have trained a recurrent neural network based on 1 stack of LSTM cells. I use it to solve a classification problem. The RNN cell has 48 hidden states. The output of the last unfolded LSTM cell is ...
1
vote
0answers
44 views

KnnBasic vs KnnWithMeans

I'm learning a bit about the use of the Surprise library and I have a set of data with users and ratings. I'm training a network with this library, using KNNBasic and KNNWithMeans, this last algorithm ...
0
votes
0answers
11 views

Consecutive frames can be discarded when training an SSD/YOLO?

Let's say I have a number of videos, and I want to train an SSD/YOLO (or FRCNN) to detect objects. In the case of a large amount of videos, there will be a lot of frames extracted and transferred to ...
0
votes
0answers
33 views

Is there a RNN that can predict the next substitute in a floorball match?

Floorball is a type of floor hockey. During the game, substitutions can be made. The team is also allowed to change players any time in the game; usually, they change the whole team. Individual ...
3
votes
0answers
39 views

How to train CNN such it eliminate dependent features and focuses on independent ones?

How we should train a CNN model when training dataset contains only limited number of cases, and the trained model is supposed to predict class (label) for several other cases, which has not seen ...
0
votes
0answers
16 views

How to shape the weights or nodes during gradient training of neural network? Training with constraints?

Gradient training changes indiscriminately all the weights and nodes of the neural network. But one can imagine the situations when the training should be shaped, e.g.: One can put constraints on ...
1
vote
1answer
26 views

Neural network with logical hidden layer - how to train it? Is it policy gradient problem? Chaining NNs?

I am doing neural machine translation task from language S to language T via interlingua L. So - there is the structure: ...
0
votes
1answer
69 views

Training an AI to recognize my voice (or any voice)

I want to start a project for my artificial intelligence class about speaker recognition. Basically, I want to train my AI to detect if it's me who's speaking or somebody else. I would like some ...
1
vote
0answers
17 views

Genetic algorithm generation of fuzzy rules with artificial network adjustment of fuzzy probabilities

Are there any working AI system designs or theory to support a system where an artificial network is trained to to adjust fuzzy probabilities and modify the parameters of a genetic algorithm that ...
1
vote
3answers
92 views

Extracting algebraic constraints from the input data

I would appreciate your help with this (naive) question of mine. Given the set of points located on a circle, $x_{i}, y_{i}$ as the input data, Can a deep/machine learning algorithm infer that radius ...
0
votes
1answer
56 views

Can gradient descent training be used for nonsmooth loss functions?

I have non-smooth loss function - e.g. loss(x)=min(x, 0.5). Can gradient descent be used for training neural networks with such functions. Can gradient descent be used for fairly general, ...
3
votes
2answers
101 views

How do biological neurons weights get initialized?

When trying to map artificial neuronal models to biological facts it was not possible to find an answer regarding the biological justification of randomly initializing the weights. Perhaps this is ...
2
votes
2answers
170 views

Would AI not obsessed with winning be better citizens of the world?

Some early AI research, inspired by Claude Shannon's maze learning mouse, Theseus, sought to discover resolutions to conflict. In the case of Theseus, the goal was to resolve the conflict between the ...
1
vote
0answers
17 views

Change parameter in Karaboga's code of ABC algorithm

I'm working on a problem and need to use Karaboga's code of the ABC algorithm but I have some questions... Does this formula for calculating a parameter have to be changed: ...
1
vote
0answers
29 views

Exploration rate decay and training in Q learning

I'm trying to replicate the results of the DeepMind's paper with Breakout included in OpenAI Gym. I wonder how much frames should I keep until I reach the fixed exploration rate. Actually it reaches ...
1
vote
1answer
24 views

Training by one batch of examples, what does it mean

Say I have a batch of examples, each examples represent a state: ...
1
vote
1answer
154 views

DQN Breakout adding an extra negative reward to help training?

I'm trying to train a DQN, so I'm using OpenAI gym and Breakout (Breakout-v0). I have altered the reward supplied by the environment: If the episode is not completed fully, the agent gets a -10 ...
2
votes
0answers
62 views

Regarding L0 sparsification of DNNs proposed by Louizos, Kingma and Welling

I am reading the paper on $\ell_0$ regularization of DNNs by Louizos, Welling and Kingma (2017) (Link to arxiv). In Section 2.1 the authors define the cost function as follows: $$ \mathcal{R}\left( \...
0
votes
1answer
33 views

Doubts at basic step of learning problem

Question: Express each of the following tasks in the framework of learning from data by specifying the input space X, output space Y, target function f:X->Y and the specifics of the data set that we ...
1
vote
0answers
32 views

Train a recurrent neural network by concatenating time series. Is it safe?

As the title says, I want to train a Jordan network (i.e. a particular kind of recurrent neural network) using a certain number of time series. Let's say that $x_1, x_2, \ldots x_N$ are $N$ input ...
0
votes
1answer
39 views

Are artificial intelligence learnings or trainings transferable from one agent to the other?

One disadvantage or weakness of Artificial Intelligence today the slow nature of learning or training success. For instance, an AI agent might require a 100,000 samples or more to reach an appreciable ...
6
votes
1answer
120 views

How do I predict if it is rainy or not?

I'm building a weather station, where I'm sensing temperature, humidity, air pressure, brightness, $CO_2$, but I don't have a raindrop sensor. Is it possible to create an AI which can say if it's ...
0
votes
1answer
160 views

How to add external training in chatterbot?

I created a very simple bot to learn how to use chatterbot. This library already comes with a training, but I wanted extra training with an import of a corpus in Portuguese that I found in github. <...
0
votes
1answer
69 views

How should one standardize input when transfer learning

Assume one is using transfer learning via a model which was trained on imagenet. Assume that the pre-processing which was used to achieve the pretrained model contained z-score standardization ...
-1
votes
1answer
51 views

How to perform PCA in the validation/test set?

I was using PCA in my whole dataset (and after split to training, validation and test), but after some researchs I found out that is wrong way to do. Then I have few questions: -Are there some ...
0
votes
0answers
10 views

Time-management while training network : need advices

I'm not sure this question is in the right Stack Exchange website, but I thought this place is a good starting point, because of the experience of users. This question is not about artificial ...
2
votes
1answer
40 views

Influence of location on a Neural Network trained for parking detection occupancy

I loaded a neural network model trained with Caffe by other people in OpenCV. The model should detect the presence of a car in a single parking spot outputting the probability of it being free/...
5
votes
1answer
931 views

Why L1/L2 regularization technique did not improve my accuracy?

I am training a Multilayer Neural Nets with 146 samples (97 for training set, 20 for validation set and 29 for testing set). I am using: automatic differentiation, SGD method, fixed learning rate + ...
6
votes
1answer
82 views

Q-Learning the generic maze solution

After doing some exercices on Q-learning for maze solving, I wondered : my q-learning algorithms solve only ONE maze. The AI doesn't learn how to solve mazes, so how can I achieve it ? For instance ...
1
vote
1answer
69 views

Is 1mb an acceptable memory size for images being trained in a CNN?

I am using Tensorflow CNN to build an image classification/prediction model. Currently all the images in the dataset are each about 1mb in size. Most examples out there use very small images. The ...