Questions tagged [training]

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

Filter by
Sorted by
Tagged with
13
votes
3answers
2k views

Why are the initial weights of neural networks randomly initialised?

This might sound silly to someone who has plenty of experience with neural networks but it bothers me... Random initial weights might give you better results that would be somewhat closer to what a ...
13
votes
2answers
2k views

How are generative adversarial networks trained?

I am reading about generative adversarial networks (GANs) and I have some doubts regarding it. So far, I understand that in a GAN there are two different types of neural networks: one is generative ($...
12
votes
3answers
10k views

How to train a neural network for a round based board game?

I'm wondering how to train a neural network for a round based board game like, tic-tac-toe, chess, risk or any other round based game. Getting the next move by inference seems to be pretty straight ...
12
votes
2answers
6k 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 ...
12
votes
3answers
31k views

How do I choose the optimal batch size?

Batch size is a term used in machine learning and refers to the number of training examples utilised in one iteration. The batch size can be one of three options: batch mode: where the batch size is ...
11
votes
3answers
429 views

Can some one help me understand this paragraph from Nvidia's progressive gan paper?

Furthermore, we observe that mode collapses traditionally plaguing GANs tend to happen very quickly, over the course of a dozen minibatches. Commonly they start when the discriminator overshoots, ...
10
votes
3answers
1k views

What size of neural networks can be trained on current consumer grade GPUs? (1060,1070,1080)

is it possible to give a rule of thumb estimate about the size of neural networks that are trainable on common consumer grade GPUs? For example: The Emergence of Locomotion (Reinforcement) paper ...
9
votes
1answer
962 views

What are the best known gradient-free training methods for deep learning?

As I know, the current state of the art methods for training deep learning networks are variants of gradient descent or stochastic gradient descent. What are the best known gradient-free training ...
9
votes
1answer
175 views

Will quantum computing have any kind of effect on the development of AI? [duplicate]

Recently, according to some reports Google achieved something called 'Quantum Supremacy'. Whether its true or not remains to be seen. But my question is does Quantum Computers or the principle they ...
8
votes
2answers
228 views

What is the name of a human-inspired machine learning approach?

I once came across a neural network being trained without back-propagation or genetic algorithms (or using any kind of data sets). It was based on how the human brain learns and adjusts its ...
8
votes
1answer
692 views

Why does 'loss' change depending on the number of epochs chosen?

I am using Keras to train different NN. I would like to know why if I increment the epochs in 1, the result until the new epoch is not the same. I am using shuffle=False, and np.random.seed(2017), and ...
7
votes
5answers
2k views

How can action recognition be achieved?

For example, I would like to train my neural network to recognize the type of actions (e.g. in commercial movies or some real-life videos), so I can "ask" my network in which video or movie (and at ...
7
votes
7answers
8k views

Why does training an SVM take so long? How can I speed it up?

I'm trying to create and test non-linear SVMs with various kernels (RBF, Sigmoid, Polynomial) in scikit-learn, to create a model which can classify anomalies and benign behaviors. My dataset includes ...
6
votes
2answers
191 views

How to shorten the development time of a neural network?

I am developing an LSTM for sequence tagging. During the development, I do various changes in the system, for example, add new features, change the number of nodes in the hidden layers, etc. After ...
6
votes
3answers
6k 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
208 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 ...
6
votes
2answers
144 views

Evolving network in game

So I wrote simple feed forward neural network that plays tic-tac-toe: 9 neurons in input layers: 1 - my sign, -1 - opponent's sign, 0 - empty; 9 neurons in hidden layer: value calculated using Relu; ...
6
votes
1answer
110 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) ...
6
votes
3answers
1k views

Does the model learn from the average of all the data points in the mini-batch?

I used the example at - https://github.com/aymericdamien/TensorFlow-Examples/blob/master/examples/5_DataManagement/tensorflow_dataset_api.py - to create my own classification model. I used different ...
6
votes
2answers
86 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 ...
6
votes
0answers
91 views

How do neural network topologies affect GPU/TPU acceleration?

I was thinking about different neural network topologies for some applications. However, I am not sure how this would affect the efficiency of hardware acceleration using GPU/TPU/some other chip. If, ...
6
votes
3answers
159 views

Why do neural networks trained on identical datasets and with identical hyper-parameters have different performances? [closed]

I found that fully connected neural networks trained on identical data sets with identical hyper-parameters can have different performances or accuracies (7-8% of deviation). Is this an unusual ...
5
votes
5answers
2k views

How does an activation function's derivative measure error rate in a neural network?

A blog post called "Text Classification using Neural Networks" states that the derivative of the output of a sigmoid function is used to measure error rates. What is the rationale for this? I ...
5
votes
2answers
920 views

What is the purpose of the batch size in neural networks?

Why is a batch size needed to update the weights of a neural network? According to that Youtube Video from 3B1B, the weights are updated by calculating the error between expectation and outcome of ...
5
votes
3answers
60 views

What should we do when we have equal observations with different labels?

Suppose we have a labeled data set with columns $A$, $B$, and $C$ and a binary outcome variable $X$. Suppose we have rows as follows: ...
5
votes
1answer
149 views

Why evolutionary training of neural networks is not popular?

Evolutionary algorithms are mentioned in some sources as a method to train a neural network (finding weights, not hyperparameters). However, I have not heard about one practical application of such an ...
5
votes
1answer
906 views

What happens to the training data after your machine learning model has been trained?

I am completely new to all this, for the life of me I can't find the answer to this question anywhere on Google. What happens after you have used machine learning to train your model? What happens to ...
5
votes
3answers
1k 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 ...
5
votes
1answer
173 views

Is it feasible to train a Machine Learning Model (with image inputs) in an average personal computer?

There are lots of examples of machine learning systems that can recognize objects and extract other information from images with very high precision. To train the models of such systems is necessary (...
5
votes
1answer
137 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 ...
5
votes
1answer
267 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 ...
5
votes
2answers
82 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 ...
4
votes
4answers
1k 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 ...
4
votes
2answers
2k views

What is the "thing" which is trained in AI model training

I am a newbie in the fantastic AI world, I have started my learning recently. After a while, my understanding is, we need to feed in tremendous data to train a or many models. Once the training is ...
4
votes
2answers
339 views

Iteratively and adaptively increasing the network size during training

For an experiment that I'm working on, I want to train a deep network in a special way. I want to initialize and train a small network first, then, in a specific way, I want to increase network depth ...
4
votes
3answers
674 views

Why should weights of Neural Networks be initialized to random numbers?

Premise Ok, I know that this question was asked before on ai.SE, on stats.SE and also on SO. So I did my homework in checking before posting my question, but none of them has an answer that fully ...
4
votes
3answers
193 views

Would this relatively small dataset be enough to train a CNN?

Scenario: I am trying to create a dataset with images of choice for different animal classes. I am going to train those images for classification using CNN. Problem: Let's assume I somehow don't have ...
4
votes
2answers
915 views

Wouldn't convolutional neural network models work better without flattening the input in any stages?

The above model is what really helped me understand the implementation of convolutional neural networks, so based on that, I've got a tricky hypothesis that I want to find more about, since actually ...
4
votes
2answers
7k 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 ...
4
votes
3answers
1k views

What does end-to-end training mean?

In simple words, what does end-to-end training mean, in the context of deep learning?
4
votes
3answers
97 views

If the accuracy of my current model is low ($50 \%$) and we want to minimize time in collecting more data, should we try other models?

Suppose we have a data set with $4,000$ labeled examples. The outcome variable is trinary (three possible categorical values). Suppose the accuracy of a given model is "bad" (e.g. less than $...
4
votes
1answer
150 views

What approach should I use to detect faces in video game footage?

I have set myself the challenge of detecting the locations of players/bots in videos of a well known first person shooter game (this is for a youtube series I'm planning on doing). I'm not sure which ...
4
votes
2answers
189 views

As a starter: what is the form of training data for image processing

What we are doing in the image processing training. We are storing some form of data which is going to act as the knowledge or experience of the system. In which form can the system store it's ...
4
votes
1answer
319 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 ...
4
votes
2answers
63 views

Is stable learning preferable to jumps in accuracy/loss

A stable/smooth learning validation curve often seems to keep improving over more epochs than an unstable learning curve. My intuition is that dropping the learning rate and increasing the patience of ...
4
votes
1answer
348 views

Does training happen during NEAT?

When one uses NEAT to evolve the best fitting network for a task, does training take place in each epoch as well? If I understand correctly, training is the adjustment of the weights of the neural ...
4
votes
1answer
140 views

How are LSTM's trained for text generation?

I've seen some articles about text generation using LSTMs (or GRUs) for text generation. Basically it seems you train them by folding them out, and putting a letter in each input. But say you trained ...
4
votes
1answer
70 views

What are state-of-the-art ways of using greedy heuristics to initially set the weights of a Deep Q-Network in Reinforcement Learning?

I am interested in the current state-of-the-art ways to use quick, greedy heuristics in order to speed up the learning in a Deep Q-Network in Reinforcement Learning. In classical RL, I initially set ...
4
votes
1answer
198 views

What can be done to correct for sampling bias introduced from (noisy) training data while training a DNN?

The obvious solution is to ensure that the training data is balanced - but in my particular case that is impossible. What corrections can one perform in such a scenario? I know that my training data ...
4
votes
1answer
51 views

How to compare the training performance of a model on different data input?

So I have a deep learning model and three data sets (images). My theory is that one of these data sets should function better when it comes to training a deep learning model (meaning that the model ...

1
2 3 4 5
8