Questions tagged [machine-learning]

For questions related to machine learning (ML), which is a set of methods that can automatically detect patterns in data, and then use the uncovered patterns to predict future data, or to perform other kinds of decision making under uncertainty (such as planning how to collect more data). ML is usually divided into supervised, unsupervised and reinforcement learning. Deep learning is a subfield of ML that uses deep artificial neural networks.

701 questions with no upvoted or accepted answers
Filter by
Sorted by
Tagged with
14
votes
1answer
221 views

Will parameter sweeping on one split of data followed by cross validation discover the right hyperparameters?

Let's call our dataset splits train/test/evaluate. We're in a situation where we require months of data. So we prefer to use the evaluation dataset as infrequently as possible to avoid polluting our ...
14
votes
3answers
351 views

Why does Batch Normalization work?

Adding BatchNorm layers improves training time and makes the whole deep model more stable. That's an experimental fact that is widely used in machine learning practice. My question is - why does it ...
9
votes
0answers
112 views

Why is my GAN more unstable with bigger networks?

I am working with generative adversarial networks (GANs) and one of my aims at the moment is to reproduce samples in two dimensions that are distributed according to a circle (see animation). When ...
9
votes
2answers
347 views

Back-of-the-envelope machine learning (specifically neural networks) calculations

There is a popular story regarding the back-of-the-envelope calculation performed by a British physicist named G. I. Taylor. He used dimensional analysis to estimate the power released by the ...
8
votes
1answer
177 views

How to deal with a small amount of labeled samples?

I'm trying to develop skills to deal with very small amounts of labeled samples (250 labeled/20000 total, 200 features) by practicing on Kaggle "Don't Overfit" dataset (Traget_Practice have ...
7
votes
1answer
96 views

How does the network know which objects to track in the paper "Label-Free Supervision of Neural Networks with Physics and Domain Knowledge"?

I was reading the paper Label-Free Supervision of Neural Networks with Physics and Domain Knowledge, published at AAAI 2017, which won the best paper award. I understand the math and it makes sense. ...
7
votes
1answer
63 views

Video summarization similar to Summe's TextRank

We have the popular TextRank API which given a text, ranks keywords and can apply summarization given a predefined text length. I am wondering if there is a similar tool for video summarization. ...
6
votes
1answer
281 views

An intuitive explanation of Adagrad, its purpose and its formula

It (Adagrad) adapts the learning rate to the parameters, performing smaller updates (i.e. low learning rates) for parameters associated with frequently occurring features, and larger updates (i.e. ...
6
votes
1answer
284 views

Which neural networks are suitable for visual place recognition?

I am doing a project on visual place recognition in changing environments. The CNN used here is mostly AlexNet, and a feature vector is constructed from layer 3. Does anyone know of similar work ...
5
votes
0answers
104 views

$\frac{P(x_1 \mid y, s = 1) \dots P(x_n \mid y, s = 1) P(y \mid s = 1)}{P(x \mid s = 1)}$ indicates that naive Bayes learners are global learners?

I am currently studying the paper Learning and Evaluating Classifiers under Sample Selection Bias by Bianca Zadrozny. In section 3. Learning under sample selection bias, the author says the following: ...
5
votes
0answers
113 views

Are there any easy ways to create annotated training images for object detection?

For the purposes of object detection, are there any easy ways to create annotated training images? For example, if we have $10,000$ images and want to draw bounding boxes on 2 objects for each image, ...
5
votes
1answer
84 views

Why would the application of boosting prevent underfitting?

"Why would the application of boosting prevent underfitting?" I read in some paper that applying boosting would prevent you from underfitting. Why is that? Source: https://www.cs.cornell.edu/...
5
votes
1answer
155 views

How do big companies, like Facebook, model individuals and their interaction?

As a layman in AI, I want to get an idea of how big data players, like Facebook, model individuals (of which they have so many data). There are two scenarios I can imagine: Neural networks build ...
5
votes
1answer
89 views

Correcting 'bad' translations in a sequence-to-sequence neural machine translation model

In working with basic sequence-to-sequence models for machine translation I have been able to achieve decent results. But inevitably some translations are not optimal or just flat-out incorrect. I am ...
4
votes
1answer
113 views

Which neural network can I use to solve this constrained optimisation problem?

Let $\mathcal{S}$ be the training data set, where each input $u^i \in \mathcal{S}$ has $d$ features. I want to design an ANN so that the cost function below is minimized (the sum of the square of ...
4
votes
0answers
265 views

When computing the ROC-AUC score for multi-class classification problems, when should we use One-vs-Rest and One-vs-One?

The sklearn's documentation of the method roc_auc_score states that the parameter multi_class can take the value ...
4
votes
1answer
131 views

Can models get 100% accuracy on solved games?

I had a question today that I feel it must have an answer already, so I'm shopping around. If we ask a model to learn the binary OR function, we get perfect accuracy with every model (as far as I know)...
4
votes
0answers
94 views

Is there a mathematical formula that describes the learning curve in neural networks?

In training a neural network, you often see the curve showing how fast the neural network is getting better. It usually grows very fast then slows down to almost horizontal. Is there a mathematical ...
4
votes
1answer
504 views

What is the input for the prior model of VQ-VAE?

I'm trying to implement the VQ-VAE model. In there, a continuous variable $x$ is encoded in an array $z$ of discrete latent variables $z_i$ that are mapped each to an embedding vector $e_i$. These ...
4
votes
0answers
90 views

How do the relative number of cells between neighboring stacked LSTM layers affect the network's behavior?

It seems that stacking LSTM layers can be beneficial for some problem settings in order to learn higher levels of abstraction of temporal relationships in the data. There is already some discussion on ...
4
votes
0answers
143 views

What characteristics make it difficult for a Neural Network to approximate a function?

What are the characteristics which make a function difficult for the Neural Network to approximate? Intuitively, one might think uneven functions might be difficult to approximate, but uneven ...
4
votes
0answers
53 views

What is the motivation for row-wise convolution and folding in Kalchbrenner et al. (2014)?

I was reading the paper by Kalchbrenner et al. titled A Convolutional Neural Network for Modelling Sentences and I am struggling to understand their definition of convolutional layer. First, let's ...
4
votes
0answers
68 views

Does overfitting imply an upper bound on model size/complexity?

Suppose that I have a model M that overfits a large dataset S such that the test error is 30%. Does that mean that there will always exist a model that is smaller and less complex than M that will ...
4
votes
0answers
639 views

Is there any way and any reason why one would introduce a sparsity constraint on a deep auto-encoder?

Is there any way and any reason why one would introduce a sparsity constraint on a deep autoencoder? In particular, in deep autoencoders, the first layer often has more units than the dimensionality ...
4
votes
0answers
122 views

Supervised K-means clustering doesn't appear to work

I have a data set containing actions taken by customers (e.g., view a product, add a product to cart, purchase product), the product bought (if any) and times of said actions. I am attempting to use K-...
4
votes
4answers
706 views

Use Machine/Deep Learning to Guess a String

I want to be able to input a block of text and then have it guess a string within a predefined range (i.e. a string that starts with three letters and ends with five numbers like "XXX12345", etc). ...
4
votes
1answer
216 views

Training RNN's on text: Can you use an ASCII encoding just as well as a one-hot character encoding?

I've mostly seen (e.g. in The Unreasonable Effectiveness of Recurrent Neural Networks) that when training RNN on text for something like language modeling, the text is usually featurized character-by-...
4
votes
0answers
168 views

How to feed a variable size sequences into a CNN?

If I want to train a convoluted NN on time series but I cannot decide where to split the data. I see that other people use jumping window over the input. so the feed say 20 sec of observation as 1 ...
4
votes
1answer
776 views

Traveling salesman problem variant: which algorithm to choose?

I have an industrial problem which I'm trying to cast as a Traveling Salesman problem (TSP) in 3D euclidian space. There are physical limitations which implies that some subpaths may or may not be ...
4
votes
2answers
85 views

How should I select the features for predicting diseases (in particular when patients specify their health issues)?

My aim is to train a model for predicting diseases. Now, according to this Wikipedia article, diseases are classified based on the following criteria in general: Causes (of the disease) Pathogenesis (...
3
votes
0answers
57 views

Which algorithms are used to locate objects in a 3d space?

I can see mobile apps that can locate a 3D object on a surface with a mobile camera and you can turn around that object. What is the name of the algorithm(s) that is used for that purpose? Or, is ...
3
votes
1answer
66 views

A comparison of Expert Systems and Machine Learning approaches in terms of run-time-efficiency and time/space complexity

For part of a paper I am writing on Clinical Decision Support Systems (computer-aided medical decision making, e.g. diagnosis, treatment), I am trying to compare Expert Systems with systems based on ...
3
votes
0answers
81 views

Why is the margin attained with $\Phi=\left[2 x, 2 x^{2}\right]^{T}$ greater than the margin attained with $\Phi=\left[x, x^{2}\right]^{T}$?

I am trying to understand the solution to part 4 of problem 3 from the midterm exam 6.867 Machine learning: Mid-term exam (October 15, 2003). For reproducibility, here is problem 3. We consider here ...
3
votes
0answers
41 views

Image classification - Need method to classify "unknown" objects as "trash" (3D objects)

We have an image classifier that was built using CNN with faster R-CNN and Yolov5. It is designated to run on 3D objects. All of those objects have similar "features" structure, but the ...
3
votes
0answers
80 views

Can XGBoost solve XOR problem?

I've read that decision trees are able to solve XOR operation so I conclude that XGBoost algorithm can solve it as well. But my tests on the datasets (datasets that should be highly "xor-ish"...
3
votes
1answer
101 views

Which machine learning method can take a matrix as input?

I am pretty new to the machine learning field. I want to use an $n \times m$ matrix as the input of a model, in order to predict a vector $1 \times m$, both of real numbers. Input data are quite clean,...
3
votes
0answers
46 views

Could zero-padding affect learning in a negative way?

I implemented an LSTM with Keras to perform word ordering task (given a syntactically unordered sentence, the goal is to label ...
3
votes
0answers
44 views

Is maximum likelihood estimation meaningless for a dataset of only outliers?

From my understanding, maximum likelihood estimation chooses the set of parameters for the estimator that maximizes likelihood with the ground truth distribution. I always interpreted it as the ...
3
votes
0answers
79 views

Why is the loss associated with my neural network increasing?

I am currently learning neural networks using data from Touchscreen Input as a Behavioral Biometric. Basically, I am trying to predict "User ID" by training the neural network model shown ...
3
votes
1answer
122 views

How do I poison an SVM with manifold regularization?

I'm working on Adversarial Machine Learning, and have read multiple papers on this topic, some of them are mentioned as follows: Poisoning Attacks on SVMs: https://arxiv.org/pdf/1206.6389.pdf ...
3
votes
0answers
42 views

In machine learning, how can we overcome the restrictive nature of conjunctive space?

In machine learning, problem space can be represented through concept space, instance space version space and hypothesis space. These problem spaces used the conjunctive space and are very restrictive ...
3
votes
0answers
336 views

Can Bert be used to extract embedding for large categorical features?

I've lot of training data points (i.e in millions) and I've around few features but the issue with that is all the features are categorical data with 1 million+ categories in each. So, I couldn't use ...
3
votes
0answers
36 views

Rarely predict minority class imbalanced datasets

I have a dataset in which class A has 99.8%, class B 0.1% and class C 0.1%. If I train my model on this dataset, it predicts always class A. If I do oversampling, it predicts the classes evenly. I ...
3
votes
0answers
71 views

DQN, how to choose the reward fucntion?

I built a simple AI system that tries to solve the 8 puzzle using DQN. The problem is, if the agent gets only a reward greater than zero when winning, the training will take a long time, so I made a ...
3
votes
0answers
31 views

Which hyper-parameters are considered in neural architecture search?

I want to understand automatic Neural Architecture Search (NAS). I read already multiple papers, but I cannot figure out what the actual search space of NAS is / how are classical hyper-parameters ...
3
votes
0answers
92 views

What is the difference between random and sequential sampling from the reply memory?

I was working on an RL problem and I am confused at one specific point. We use replay memory so that the network learns about previous actions and how these actions lead to a success or a failure. ...
3
votes
1answer
142 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
26 views

Reverse engineering controller sensitivity/aim for several games ie acceleration curves, deadzones, etc

A machine learning project I am working on requires me to interface with an Xbox controller connected to a PC. The implementation must do the following two things: Record the joystick input from the ...
3
votes
0answers
179 views

What are the differences between CRF and HMM?

What I know about CRF is that they are discriminative models, while HMM are generative models, but, in the inference method, both use the same algorithm, that is, the Viterbi algorithm, and forward ...
3
votes
0answers
43 views

Where could I find information on the learning methods used in Neurogrid?

I have been searching for more than one week which learning methods were used in Neurogrid. But I only found descriptions of its architecture (chips, circuits, analog and/or digital components, ...

1
2 3 4 5
15