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.

Filter by
Sorted by
Tagged with
0
votes
0answers
12 views

Larger neural network with almost similar training and validation error as smaller network

I am building a neural network that takes as input 202 units and outputs a 200 dimension continuous variable. While trying to find the best model, one of the parameters i tune is the the number of ...
2
votes
0answers
27 views

What is the gradient of the Q function with respect to the policy's parameters?

I have been recently studying Actor-Critic algorithms, and I ran into the following question. Let $Q_{\omega}$ be the critic network, and $\pi_{\theta}$ be the actor. It is known that in order to ...
0
votes
0answers
12 views

Best ways of leveraging AI for stock market trading

What are the current popular approaches to leveraging AI for stock price prediction? It seems like there could be several approaches and problem formulations: Supervised learning: Regression: ...
1
vote
0answers
25 views

How do I approach this problem?

Let's say I have a dataset with multiple types of multiple ingredients (salt1,salt2, etc). Each n-th variation of each ingredient vs flavor may be represented by an n×k matrix that where an ingredient ...
1
vote
1answer
19 views

What is the meaning of “easy negatives” in the context of machine learning?

What does the term "easy negatives" exactly mean in the context of machine learning for a classification problem or any problem in general? From a quick google search, I think it means just negative ...
0
votes
0answers
11 views

Deep Network with constraint or auxiliary features

The target of my current neural network is to predict a label. The dataset contains some features, there is a label $y_i$ in transaction $i$, indicating its classification. There is one feature $f^{i}...
1
vote
1answer
30 views

How is an architecture composed of a second model that validates the first one called in machine learning?

I have a mix of two deep models, as follows: if model A is YES --pass to B--> if model B is YES--> result = YES if model A is NO ---> result = NO So ...
1
vote
1answer
38 views

Why is probability that at least one hypothesis out of $k$ being consistent with $m$ training examples $k(1- \epsilon)^m$?

My question is actually related to the addition of probabilities. I am reading on computational learning theory from Tom Mitchell's machine learning book. In chapter 7, when proving the upper bound ...
2
votes
1answer
36 views

What are the best classifiers for this type of data?

I would like to classify a dataset Credit Scoring, which is composed of 21 attributes, some of them are numeric and others are boolean. For the output, I want to know if they have a good or bad ...
1
vote
0answers
7 views

Using AI to find the correct set of object/numbers based on previous data

There are 11 objects of which 4 are "Bad" objects. So there are 7 "Good" objects. You have to choose as many Good objects before proceeding to another set of objects of a different sequence. How ...
4
votes
2answers
460 views

Does the “lowest layer” refer to the first or last layer of the neural network?

People sometimes use 1st layer, 2nd layer to refer to a specific layer in a neural net. Is the layer immediately follows the input layer called 1st layer? How about the lowest layer and highest layer?...
0
votes
1answer
39 views

Is an SVM the same as a neural network without a hidden layer?

A neural network without a hidden layer is the same as just linear regression. If I then use squared hinge loss and encoporate the l2 regularisation term, is it fair to then call this network the ...
2
votes
1answer
30 views

A model for each sub-problem vs one model for the whole problem

Let's say one wants to use a neural net to learn some function $g(x)$. Let's say that we know that $g$ is a combination of two functions (or two sub-problems), $g(x)=f_2(f_1(x))$, and that we have two ...
1
vote
0answers
30 views

How can I approximate a function that determines the priority of objects?

I am facing the following supervised learning problem: An object is fully characterized by its position in $R^n$. There are $m$ objects. There are fully observable (i.e. their positions are always ...
1
vote
0answers
14 views

Are there any novel quantum machine learning algorithms that are fundamentally different from “classical” ones?

Generally, if one googles "quantum machine learning" or anything similar the general gist of the results is that quantum computing will greatly speed up the learning process of our "classical" machine ...
3
votes
1answer
40 views

How can a single sample represent the expectation in gradient temporal difference learning?

I was reading the gradient temporal difference learning version 2(GTD2) from rich Sutton's book page-246. At some point, he expressed the whole expectation using a single sample from the environment. ...
1
vote
0answers
38 views

What is the relationship between PAC learning and classic parameter estimation theorems?

What are the differences and similarities between PAC learning and classic parameter estimation theorems (e.g. consistency results when estimating parameters, e.g. with MLE)?
0
votes
0answers
19 views

Can neural networks always be assembled like Lego blocks?

BACKGROUND Consider a supervised problem which is based on two scalar features (1) and (2) as well as a third, "time-dependent", feature consisting of a sequence of five values (3)-(7). For ...
0
votes
1answer
30 views

Why are all weights of a neural net updated and not just the weights of the first layer

Why are all weights of a neural net updated and not only the weights of the first hidden layer? The error-influence of the prediction by the weights of a neural net is calculated using the chain rule....
0
votes
1answer
21 views

Is radial basis function network appropriate for small datasets?

I'm a computer engineering student and I'm about to work on my master thesis. My professor gave me a small dataset with brain Computed Axial Tomography records. I would like to use deep learning to ...
0
votes
0answers
48 views

How can I group the entries of the network traffic by their similarity?

I have the traffic of my network (with hundreds of entries). Below I am showing only 9 entries. ...
1
vote
0answers
6 views

How does optical computing work and deal with nonlinearity?

This article states that: One of the algorithms that photonics is very good at implementing is matrix multiplication But how are parameters stored and updated(in backpropagation)? One more ...
0
votes
0answers
26 views

How to convert something to vectors

I wanted to create an encoder, which is the first part of an autoencoder. I do not want to build the whole autoencoder but rather wanted to test whether my mobile device can support running an encoder ...
2
votes
1answer
65 views

What are examples of machine learning techniques inspired by neuroscience?

What are examples of machine learning techniques (i.e. models, algorithms, etc.) inspired (to different extents) by neuroscience? Particularly, I'm interested in recent developments, say less than 10 ...
0
votes
0answers
15 views

What are the best human re-identification methods available?

I have a use case where I need to detect, track and re-identify humans in CCTV footage. I have usedSSD and Median Flow to detect ...
1
vote
0answers
36 views

Why is the number of neurons used in various neural networks power of 2?

I have noticed that almost all tutorials take the number of neurons as a power of 2. Is there any proper mathematical and well-proven reason for that? If you sometimes change it to some other odd ...
0
votes
0answers
16 views

Are there any good research papers on image identification with limited data?

I'm a newbie in machine learning and I am interested in neural networks. Are there any good research papers on image identification with limited data?
0
votes
0answers
12 views

AI for creating random 2D contour lines based on learnt images

I am new to AI and want to expand into this field. For our software we often could use a virtual device which generates 2D point data (a contour of some assembly part). Hypothetically using a set of ...
1
vote
1answer
49 views

Finding patterns in binary files using deep learning

I am a newbie in deep learning and wanted to know if the problem I have at hand is a suitable fit for deep learning algorithms. I have thousands of fragments each of about 1000 bytes size (i.e. ...
0
votes
2answers
59 views

Can techniques like the Pomodoro be applied to AI systems? [closed]

The Pomodoro technique may improve the learning efficiency of humans. Can these techniques also be applied to AI systems? If so, what impact might it have?
1
vote
1answer
47 views

What do we mean by saying “VC dimension gives a LOOSE, not TIGHT bound”?

From what I understand VC dimension is what establishes the feasibility of learning for infinite hypothesis sets, the only kind we would use in practice. But, the literature (i.e. Learning from Data)...
0
votes
0answers
17 views

Understanding an extract on the motivation behind residual networks

I was reading about ResNets from this page, and I couldn't understand the following extract, about the motivation behind ResNets: "Since neural networks are good function approximators, they ...
2
votes
1answer
30 views

Is there a notion of generalization in unsupervised learning?

I've been learning a little bit about generalization theory, and in particular, the PAC (and PAC-Bayes) approach to thinking about this problem. So, I started to wonder if there is an analogous ...
1
vote
1answer
54 views

Why does this model have 12 parameters?

I guess the model shown in this image (img_1) is the same as the one in this image (img_2) I was trying to build a neural net like that. This keras code is to do the job. ...
2
votes
2answers
45 views

Could clustering be used to parse pdf documents to get headings and titles?

I'm a bit new to AI and I'd like to use some kind of clustering algorithm to solve a problem: I'm trying to parse pdf documents to get headings and titles. I can parse pdf to html and I'm then able ...
5
votes
4answers
374 views

How does size of the dataset depend on VC dimension?

This might be a little broad question, but I have been watching Caltech youtube videos on Machine Learning, and in this video prof. is trying to explain how we should interpret VC dimension in terms ...
3
votes
4answers
461 views

What are the pros and cons of studying machine learning before deep learning?

I'm a biotech student and I'm currently working on single-particle tracking. For my work, I need to use aspects of deep learning (CNN, RNN and object segmentation) but I'm not familiar with these ...
2
votes
1answer
47 views

An infinite VC dimensional space vs using hierarchical subspaces of finite but growing VC dimensions

I have the following scenario. I have a binary classification problem, whose underlying function is a step function. The probability distribution of feature vectors is a uniform over the domain. Case ...
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 ...
1
vote
1answer
38 views

Machine learning to find coordinate in image

I am trying to figure out how to approach this. Given training data of images and the pixel coordinates of the centre of an object in that image, would it be possible to predict the pixel coordinates ...
3
votes
1answer
34 views

How to add weights to one specific input feature to ensure fair training in the network?

I am trying to create a multiclass product-rating network based on product reviews and other input features. Two of the other input features are "product category" and "gender". However, I want to ...
1
vote
2answers
19 views

How is a validation set used to tune the hyperparameters in a non-biased way, if the new models depends on the values of these?

I've built a neural network from the scratch, choosing arbitrary numbers for the hyperparameters: learning rate, number of hidden layers and neurons for these, number of epochs and size of mini ...
1
vote
1answer
47 views

Understanding relation between VC Symmetrization Lemma and Generalization Bounds

I am new in the field of Machine Learning so I wanted to start of by reading more about mathematics and history behind it. I am currently reading, in my opinion, a very good and descriptive paper on ...
2
votes
2answers
54 views

Could machine learning be used to measure the distance between two objects from a picture or live camera?

Could machine learning be used to measure the distance between two objects from a picture or live camera? An example of this is the measurement between the centre of each eye pupil. This area is ...
2
votes
1answer
18 views

How are weights for weighted x-entropy loss on imbalanced data calculated?

I am trying to build a classifier which should be trained with the cross entropy loss. The training data is highly class-imbalanced. To tackle this, I've gone through the advice of the tensorflow docs ...
2
votes
2answers
37 views

Is there an online tool that can predict accuracy given only the dataset?

Is there an online tool that can predict accuracy given only the dataset as input (i.e. without the compiled model)? That would help to understand how data augmentation/distribution standardization, ...
2
votes
0answers
27 views

Creating Dataset for Image Classification

I want to develop a CNN model to identify 24 hand signs in American Sign Language. I created a custom dataset that contains 3000 images for each hand sign i.e. 72000 images in the entire dataset. For ...
1
vote
0answers
42 views

Why does the growth function need to be polynomial in order for the learning algorithm to be consistent?

Could someone please explain to me why in VC theory, specifically, when calculating the VC dimension, the growth function needs to be polynomial in order for the learning algorithm to be consistent? ...
3
votes
1answer
53 views

Are Q values estimated from a DQN different from a duelling DQN with the same number of layers and filters?

I am confused about the Q values of a duelling deep Q network (DQN). As far as I know, duelling DQNs have 2 outputs Advantage: how good it is to be in a particular state $s$ Value: the advantage of ...
2
votes
0answers
24 views

Possible approaches to dealing with unbalanced dataset and highly biased deep learning algorithm

I have an extremely unbalanced video dataset for a two class video classification problem.All my videos in my current video dataset is $40$ second long with $900p$ resolution.However the dataset is ...

1
2
3 4 5
30