Questions tagged [training]

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

64 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
8
votes
3answers
271 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, ...
6
votes
2answers
65 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 ...
3
votes
0answers
15 views

How to organize model training hyperparameters

I am working on multiple deep learning projects, most of them in the area of computer vision. For many of them I create multiple models, try different approaches, use various model architectures. And ...
3
votes
0answers
27 views

How to train a model to extract custom and unknown entities

I'm trying to figure out how to extract specific text from an utterance by a user. I need to extract "unknown" text from a short and simple text. In this case, the user wants to create a list. ...
3
votes
0answers
40 views

When to use RMSE as opposed to MSE and vice versa?

I understand that RMSE is just the square root of MSE. Generally, as far as I have seen, people seem to use MSE as a loss function and RMSE for evaluation purposes, since it exactly gives you the ...
3
votes
0answers
78 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 ...
3
votes
0answers
50 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 ...
3
votes
1answer
48 views

GPU/TPU acceleration for neural networks with various network topologies

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, ...
2
votes
0answers
43 views

What form of output would be needed to train a model on a connect 4 AI?

I've had a big interest in machine learning for a while, and I've followed along a few tutorials, but have never made my own project. After losing many games of connect 4 with my friends, I decided to ...
2
votes
1answer
42 views

REINFORCE algorithm for portfolio optimization - problem while training

I'm trying to implement the Reinforce algorithm (Monte Carlo policy gradient) in order to optimize a portfolio of 94 stocks on a daily basis (I have suitable historical data to achieve this). The idea ...
2
votes
0answers
162 views

How to transfer learn Darknet YOLOv3

I've started getting into object detection in image. I have YOLOv3 neural network with Darknet framework. The network is pre-trained from COCO data set. Now I need to do some transfer learning in ...
2
votes
0answers
38 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 ...
2
votes
0answers
28 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 ...
2
votes
3answers
111 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 ...
2
votes
0answers
64 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( \...
2
votes
0answers
98 views

Performance Evaluation Metrics used in Training, Validation and Testing

Which specific performance evaluation metrics are used in training, validation and testing and why? I am thinking error metrics (RMSE, MAE, MSE) are used in validation, and testing should use a wide ...
2
votes
0answers
40 views

Shifting training data

I want to create a neural network and train it on some data, however I want to be able to create a new model without retraining it from the start. An example, I have 1000 data points in my training ...
2
votes
0answers
82 views

Classification Learning - Normalization of time series and live usage

UPDATE: The tables look messed up so i put them on pastebin for better visibility. https://pastebin.com/gDX28uVF I am using Neural Network with different learning types (for example Standard ...
2
votes
1answer
388 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
0answers
74 views

How would I implement this New Type of NN

CIO NN CIO NN stands for Controller Input Output Nerual Network note due to a typo the "nearon" means "neron" For this we have to redefine the Nearon 2 Inputs 2 Outputs 4 Weights (each input and ...
2
votes
0answers
46 views

Recommendations on which architecture to use to guess appointment

I'm currently developping an application which allows psychologists to manage their schedule and budget. As a proof of concept, I would like to create an intelligent appointment service. There can be ...
2
votes
0answers
103 views

Train, Validation and Test Split for Reporting Accuracy of Neural Model and BOW

I need to report accuracies of my neural model in a conference paper as compared to various baselines. What are the accepted standards for reporting accuracies in a fair manner? Neural Model: To be ...
2
votes
0answers
525 views

3D - CNN. Why my cost function decreases, but the accuracy does not increase?

I'm implementing a C3D-inspired neural network for human emotion recognition, the problem I'm facing is that altough the cost function is decreasing, for both training and validation sets, I do not ...
1
vote
0answers
22 views

How to change the architecture of my simple sequential model

I'm new to Deep Learning with Keras. With some tutorials online for cat vs non-cat classification, I was able to compile this simple architecture for my own ...
1
vote
0answers
27 views

Finetuning GPT-2 twice for particular style of writing on a particular topic

Sorry if this is a stupid question. I'm just starting out in ML and am working with gpt-2 for text generation. My situation is that I have to generate text in a particular field for eg. family ...
1
vote
0answers
11 views

A NN based model of a Cattle for 'Heat Detection'

I am very new to AI/ML but have lot of interest in these. I am trying to understand how this gadget works. So far I have understood that a NN model of the cattle is generated by offline ...
1
vote
0answers
19 views

Train detector : 300 images with 30 objects or 9000 images with one?

so I have this dataset of images of people sitting in a restaurant. I've annotated about 300 images with an average of 30 instances of "person" per image. Now I'm wondering if I should have annotated ...
1
vote
0answers
29 views

AI for Warcraft 3 Dota

I want to create AI for Dota1. Is it possible to create AI for Warcraft 3? How Open AI works in Dota2? I want to know more about algorithms what are in foundation in Open AI.
1
vote
0answers
20 views

i have trained my model & now trying to predict but unable to do using keras

i have trained my model & now trying to predict but unable to do please help. trying to predict cat or dog stuck in "prediction" ...
1
vote
0answers
12 views

Binary annotations on large, heterogenous images

I'm working on a deep learning project and have encountered a problem. The images that I'm using are very large and extremely detailed. They also contain a huge amount of necessary visual information, ...
1
vote
2answers
68 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
0answers
29 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
161 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 ...
1
vote
0answers
18 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
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
38 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
0answers
37 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 ...
1
vote
0answers
19 views

Adding voices to voice synthesis corpuses

If one uses one of the open source implementations of the WaveNet generative speech synthesis design, such as https://r9y9.github.io/wavenet_vocoder/, and trains using something like the CMU's arctic ...
1
vote
0answers
63 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 ...
1
vote
0answers
36 views

What methods are there to detect discrimination in trained models?

I've been researching AI regulation and compliance (see my related question on law.stackexchange), and one of the big take-aways that I had is that the regulations that apply to a human will apply to ...
1
vote
0answers
77 views

Object recognition by two or more traits that are orthogonal (informally speaking)

I would really appreciate if someone could comment the following method of training neural nets providing them with some meta data (Making them more color prone only if needed, whereas now they're ...
1
vote
0answers
124 views

My network does always predict always the first right class

I trained my model ResNet-50 for UCMerced_LandUse dataset and this my loss graph but I have a problem when I try my first picture ...
1
vote
0answers
223 views

Transfer learning from model trained in a similar dataset

I am currently working on a defect detection algorithm but I only have a few samples of defects.I googled for defect detection datasets and I found this one: http://resources.mpi-inf.mpg.de/...
1
vote
0answers
119 views

Natural language processing with a continuous dependent variable

I have a large number of observations. Each observation contains: dependent variable: a scores ranging from 0 - 100 independent variable: a large article I want to know which words or phrases ...
1
vote
0answers
85 views

When do you back-propagate errors through a Neural Network when using TD Lambda

I have a Neural Network that I'm want to use to self-play Connect Four. The neural network receives the board state and is to provide an estimate of the states desirability. I would then, for each ...
0
votes
0answers
6 views

AI for a 2D grid game involving two players

I'd like to create an AI for a 2D game involving two players fighting against each other. The map look something like this (The map is a NxN array somehow randomly generated): Basically the players ...
0
votes
0answers
13 views

Model training with colored images instead of grayscale

I'm new to Python and Deep Learning with Keras. With some tutorials online for cat vs non-cat classification, I was able to compile this simple training code for my ...
0
votes
0answers
26 views

creating your own dataset similar to cityscapes format

I'm trying to train a neural network with my own dataset. The neural network can accept the cityscape format. Is there any application that can give mask/segmented image, instance image, label IDs ...
0
votes
0answers
29 views

What is the state of the art AI training technique for imperfect information 2 player turn based games?

As far as I can tell (correct me if I'm wrong), Alphazero (with MCTS and neural network heuristic function RL) is the state of the art training method for turn based, deterministic, perfect ...
0
votes
0answers
7 views

Fusing label distribution and on-hot encoded labels

A while ago I came across a paper for image classification that utilized both label distribution and one-hot encoded labels to classify images. An image has a label distribution for all classes (4 ...