Questions tagged [training]

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

Filter by
Sorted by
Tagged with
1
vote
1answer
28 views

Why do we also need to normalize the action's values on continuous action spaces?

I was reading here tips & tricks for training in DRL and I noticed the following: always normalize your observation space when you can, i.e., when you know the boundaries normalize your ...
1
vote
1answer
18 views

What kind of problems cannot be solved using machine learning techniques?

For the problems that can be solved algorithmically. We have very good formal literature for which problems can be solved in polynomial, exponential time and which cannot. P/NP/NP-hard But do we ...
0
votes
1answer
22 views

What does it mean to train a model?

We hear this many time for different problems Train a model to solve this problem! What do we really mean by training a model?
2
votes
1answer
13 views

How do LSTM or GRU gates learn to specialize in their desired tasks?

While I was studying the equations for the computation inside GRU and LSTM units, I realized that although the different gates have different Weight matrices, their overall structure is the same. They ...
0
votes
0answers
16 views

How can I build a model that replaces a feature of one image with another feature?

I would like to build a neural network (using TensorFlow) that is able to take two animals, and replace a feature in the second with one in the first. For example, if given a dog and cat, the cat's ...
3
votes
1answer
24 views

What is meant by the expected BLEU cost when training with BLEU and SIMILE?

Recently I was reading a paper based on a new evaluation metric SIMILE. In a section, validation loss comparison had been made for SIMILE and BLEU. The plot showed the expected BLEU cost when training ...
2
votes
1answer
56 views

How difficult is this sound classification?

I want a microphone to pick up sounds around me (let's say beyond a 3 foot radius), but ignore sounds made at my desk, such as the rustling of paper, clicking a mouse and typing, my hands brushing up ...
2
votes
1answer
36 views

Is there a way of deriving a loss function given the neural network and training data?

There is some sort of art to using the right loss function. However, I was wondering if there is a way to derive the loss function if I gave you a neural network model (the weights) as well as the ...
2
votes
0answers
67 views

Sentence classification and named identity detection with automatic retraining

I am learning AI and trying out my first real-life AI application. What I am trying to do is taking as an input various sentences, and then classifying the sentences into one of X number of categories ...
0
votes
1answer
47 views

not sure if fine-tuned network is finely-tuned

I am practicing with Resnet50 fine tuning for binary classification task, here is my code snippet. ...
1
vote
3answers
84 views

How to improve neural network training against a large data set of points with varying magnitude

I am currently using TensorFlow and have simply been trying to train a neural network directly against a large continuous data set, e.g. $y = [0.014, 1.545, 10.232, 0.948, ...]$ corresponding to ...
0
votes
0answers
14 views

Low accuracy during training for text summarization

I am trying to implement an extractive text summarization model. I am using keras and tensorflow. I have used bert sentence embeddings and the embeddings are fed into an LSTM layer and then to a Dense ...
3
votes
1answer
161 views

How can I incrementally train a Yolo model without catastrophic forgetting?

I have successfully trained a Yolo model to recognize k classes. Now I want to train by adding k+1 class to the pre-trained weights (k classes) without forgetting previous k classes. Ideally, I want ...
5
votes
1answer
175 views

For each epoch, can I use only on a subset of the full training dataset to train the neural network?

If one has a dataset large enough to learn a highly complex function, say learning chess game-play, and the processing time to run mini-batch gradient descent on this entire dataset is too high, can I ...
3
votes
1answer
229 views

How can I reduce the GPU memory usage with large images?

I am trying to train a CNN-LSTM model. The size of my images is 640x640. I have a GTX 1080 ti 11GB. I am using Keras with the TensorFlow backend. Here is the model. ...
0
votes
0answers
9 views

Training a model for text document transformation?

I have a bunch of text documents, split into source documents and transformed documents. These text documents have multiple lines and are edited at specific locations, in a specific way. I make use ...
0
votes
0answers
13 views

How to save and load a Q-Learning Agent [migrated]

I know this may sound nooby, but how do I save a Deep Q-Learning agent's progress? I mean when I close at i.e. episode 500 when my agent is trained and I restart (in my case a pygame) my agent is ...
0
votes
2answers
45 views

Difference between training accuracy and calculating accuracy with class prediction

I have trained my neural network with a dataset of 11200 images, and its validation accuracy was 96%. I saved my model and load its weights to the same neural network. I chose 738 images of my dataset ...
1
vote
0answers
26 views

Confidence Interval around prediction with bootstrapping

I want to generate a confidence interval around my prediction (vector) $\hat{y}$. I have implemented the following procedure. However, I am not sure whether this makes sense in a statistical way: I ...
4
votes
2answers
359 views

What is the most time-consuming part of training deep networks?

Deep networks notoriously take a long time to train. What is the most time-consuming aspect of training them? Is it the matrix multiplications? Is it the forward pass? Is it some component of the ...
11
votes
2answers
3k views

Which layer in a CNN consumes more training time: convolution layers or fully connected layers?

In a convolutional neural network, which layer consumes more training time: convolution layers or fully connected layers? We can take AlexNet architecture to understand this. I want to see the time ...
6
votes
3answers
3k 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 + ...
2
votes
1answer
31 views

Is the test time the phase when the model's accuracy is calculated with test data set?

When papers talk about the "test time", does this mean the phase when the model is passed with new data instances to derive the accuracy of the test data set? Or is "test time" the phase when the ...
3
votes
3answers
116 views

What is the difference between training and testing in reinforcement learning?

In reinforcement learning (RL), what is the difference between training and testing an algorithm/agent? If I understood correctly, testing is also referred to as evaluation. As I see it, both imply ...
0
votes
0answers
8 views
3
votes
1answer
27 views

Does Q Learning learn from an opponent playing random moves?

I've created a Q Learning algorithm to play Connect Four against an opponent who just chooses a random free column. My Q Agent is currently only winning about 0.49 games on average (30,000 episodes). ...
1
vote
1answer
22 views

Should I just use exploitation after I have trained the Q agent?

When using a trained Q-learning algorithm in an actual game, would I just use exploitation and no longer use exploration? Should I use exploration only during the training phase?
0
votes
0answers
31 views

Are there any papers on this alternate neural net training approach?

I developed a custom callback for Keras. Initially, it monitors training accuracy. If on a given epoch the accuracy is below that of the previous epoch it lowers the learning rate by a factor. If for ...
1
vote
1answer
541 views

Add training data to YOLO post-training

(Cross-posting here from the data science stack exchange, as my question didn't get any replies. I hope it's okay!) I've been playing around with YOLOv3 and obtaining some good results on the ~20 ...
1
vote
1answer
297 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 ...
0
votes
0answers
30 views

Convolutional Neural Network Training on Different Datasets

I currently want to train a CNN but I have two small datasets that are slightly different because of the camera setup that captured the images. I'm interested in ultimately tuning the neural network ...
0
votes
0answers
23 views

Can neural networks handle redundant inputs?

I have a fully connected neural network with the following number of neurons in each layer [4, 20, 20, 20, ..., 1]. I am using TensorFlow and the 4 real-valued ...
1
vote
0answers
18 views

Why does this tutorial on reinforced learning not check whether the environment is 'game over' during training?

I am following the tutorial Train a Deep Q Network with TF-Agents. It uses the hello world environment of reinforced learning: cart pole. At the end, the agent is ...
3
votes
1answer
444 views

Periodic Pattern in Validation Loss Curve

I am currently trying to solve a regression problem using neural networks. I want to detect movement patterns in images over time (video) and output a continuous value. During the training process I ...
2
votes
2answers
37 views

What does it mean if classification error is equal between two networks but the MSE is different?

I'm experimenting with training a feedforward neural network using a genetic algorithm and I've done a few tests using both the mean squared error and classification error functions as fitness ...
1
vote
0answers
24 views

How to make binary neural networks resilient to flipped activation values?

Assume I am given a binary neural network where the activation values are constrained to be 0 or 1 (by clipping the ReLU function). Additionally, assume the neural network is supposed to work in a ...
1
vote
1answer
59 views

If the i.i.d. assumption holds, shouldn't the training and validation trends be exactly the same?

If the i.i.d. (independent and identically distributed) assumption holds for a training-validation set pair, shouldn't their loss trends be exactly the same, since every batch from the validation set ...
3
votes
2answers
57 views

If loss reduction means model improvement, why doesn't accuracy increase?

Problem Statement I've built a classifier to classify a dataset consisting of n samples and four classes of data. To this end, I've used pre-trained VGG-19, pre-trained Alexnet and even LeNet (with ...
1
vote
2answers
288 views

Is my GRU model under-fitting given this plot of the training and validation loss?

I was running my gated recurrent unit (GRU) model. I wanted to get an opinion if my loss and validation loss graph is good or not, since I'm new to this and don't really know if that is considered ...
1
vote
1answer
49 views

Stochastic gradient descent does not behave as expected, even with different activation functions

I have been working on my own AI for a while now, trying to implemented SGD with momentum from scratch in python. After looking around and studying all the maths behind it, i finally managed to ...
2
votes
1answer
43 views

After having selected the best model with cross-validation, for how long should I train it?

When using k-fold cross-validation in a deep learning problem, after you have computed your hyper-parameters, how do you decide how long to train your final model? My understanding is that, after the ...
1
vote
1answer
27 views

Should I be balancing the data before creating the vocab-to-index dictionary?

My question is about when to balance training data for sentiment analysis. Upon evaluating my training dataset, which has 3 labels (good, bad, neutral), I noticed there were twice as many neutral ...
2
votes
2answers
46 views

Should I always start from the same start state in reinforcement learning?

In an episodic training of an RL agent, should I always start from the same initial state or I can start from several valid initial states? For example, in a gym environment, should my ...
2
votes
1answer
22 views

Data scan not making sense for coco dataset

I am doing a simple scan to see how dataset size affects training. Basically, I took 10% of the coco dataset and trained a yolov3 net (from scratch) to just look for people. Then I took 20% of the ...
2
votes
0answers
18 views

How can I implement a Facial Recognition algorithm in C++ from scratch, without using OpenCV?

I wanna implement an algorithm for Facial Recognition in C++ with the help of Viola-Jones, aka Adaboost, but without using OpenCV or any other similar library. I wanna do it all from scratch. Any tips?...
0
votes
2answers
25 views

What does it mean to have epochs=30 in Keras' fit method given certain data?

I have read a lot of information about several notions, like batch_size, epochs, iterations, but because of explanation was without numerical examples and I am not native speaker, I have some kind of ...
0
votes
2answers
28 views

Automated Annotation of Objects

Given thousands of images, where some of the images contain target objects and others do not, is there an easy way of drawing bounding boxes on these target objects rather than relying on manual ...
4
votes
0answers
14 views

How do weights changes handles during back-propagation when there are unknown labels

I have a question about how weights are updated during back-propagation for some of my samples that have unknown labels (please note, unknown, not missing). The reason they are unknown is because this ...
6
votes
2answers
78 views

Why do very deep non resnet architectures perform worse compared to shallower ones for the same iteration? Shouldn't they just train slower?

My understanding of the vanishing gradient problem in deep networks is that as backprop progresses through the layers the gradients become small, and thus training progresses slower. I'm having a hard ...
2
votes
0answers
22 views

What could cause a big fluctuation of the loss in the last epochs of training an AlexNet?

I am training an AlexNet neural network, with about 12000 images which 80% is for training, 10% is for validation and another 10% is for testing. I have a problem in my plots. There is a big ...

1
2 3 4 5 6