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
1
vote
1answer
19 views

How powerful is OpenAI Gym/Universe in board games area?

I'm a big fan of computer board games and would like to make Python chess/go/shogi/mancala programs. Having heard of reinforcement learning, I decided to look at OpenAI Gym. But first of all, I would ...
1
vote
0answers
21 views

How to exploit translational symmetry for extrapolation in video generation using machine learning

I'll try to rephrase my problem in the context of video processing. Imagine that initial frame of video has some translational symmetry. The frame evolves according to an update rule. I generate a ...
2
votes
2answers
81 views

Are there any public real-life code examples of ML applications in Python?

Problems I often face at work usually differ from tutorial or book-like examples so I end up with a code that works but it's not elegant and takes too much time to write. I wanted to ask you if there ...
5
votes
1answer
209 views

How do recommendation systems work?

How do recommendation systems (e.g. on Youtube) work? Apparently, every user gets different recommendations depending on his location, his past liked videos, etc. So it would seem like a training ...
7
votes
1answer
612 views

Loss function for Hierarchical Multi-label classification

I am looking to try different loss functions for a hierarchical multi-label classification problem. So far, I have been training different models or submodels like multilayer perceptron ( MLP )branch ...
0
votes
2answers
158 views
2
votes
1answer
29 views

How can supervised learning be viewed as a conditional probability of the labels given the inputs?

In the literature and textbooks, one often sees supervised learning expressed as a conditional probability, e.g., $\ \ \ \ \ \rho(\vec{y}|\vec{x},\vec{\theta})$ where $\vec{\theta}$ denotes a ...
2
votes
2answers
51 views

What does “immediate vector-valued feedback” mean?

In the book Artificial Intelligence Engines: A Tutorial Introduction to the Mathematics of Deep Learning, James Stone says With supervised learning, the response to each input vector is an output ...
16
votes
3answers
10k views

What is the time complexity for training a neural network using back-propagation?

Suppose that a NN contains $n$ hidden layers, $m$ training examples, $x$ features, and $n_i$ nodes in each layer. What is the time complexity to train this NN using back-propagation? I have a basic ...
0
votes
1answer
15 views

How to train FFNN with Q-learning?

I know that in any NN architecture, the input data are states, and at the output layer Q-functionality of each action. Tell me please, how to adjust all weights in this case?
51
votes
9answers
29k views

Why is Python such a popular language in the AI field?

First of all, I'm a beginner studying AI and this is not an opinion oriented question or one to compare programming languages. I'm not implying that Python is the best language. But the fact is that ...
1
vote
0answers
19 views

What is the expected value of an IOU in this case?

I have a detection problem. An object with a probability of 0.5 is in a box with coordinates ((0,0), (2, 2)) and with a probability of 0.5 a box with coordinates ((2,0), (4,2)). What is the maximum ...
2
votes
1answer
43 views

What is “Computational Linguistics”?

It's not clear to me whether or not someone whose work aims to improve an NLP system may be called a "Computational Linguist" even when she/he doesn't modify the algorithm directly by coding. Let's ...
1
vote
1answer
39 views

Do we train a logistic regression model using a dataset that is 3 times bigger than the validation dataset?

Suppose we have a data set $X$ that is split as $X_{\text{train}}$, $X_{\text{val}}$ and $X_{\text{test}}$ and the outcome variable is binary. Let's say we train three different models (logistic ...
1
vote
1answer
31 views

How to track performance of your model during experimenting?

During weeks and months of your work, many things may change, for example : You may modify the loss function Your training or validation datasets may change You modify data augmentation Which tools ...
1
vote
0answers
21 views

OCR - Text recognition from Image

I plan to develop OCR application using tensorflow to get the value from the image. Text in the image may handwritting or text printed. From the image, my ocr appplication will able to get the value ...
1
vote
1answer
77 views

In which cases is the categorical cross-entropy better than the mean squared error?

In my code, I usually use the mean squared error (MSE), but the TensorFlow tutorials always use the categorical cross-entropy (CCE). Is the CCE loss function better than MSE? Or is it better only in ...
2
votes
0answers
18 views

Lego minifigure facial recognition: where to start?

I'm interested in starting a project that will identify the face of a Lego minifigure from a digital photo. I eventually want to do a "face swap," but I'd like to start with the challenge of ...
4
votes
3answers
130 views

How can I determine the mathematical relation between the input and output variables?

I would like to take in some input values for $n$ variables, say $R$, $B$, and $G$. Let $Y$ denote the response variable of these $n$ inputs (in this example, we have $3$ inputs). Other than these, I ...
1
vote
0answers
36 views

How is clustering used in the unsupervised training of a neural network?

How is clustering used in the unsupervised training of a neural network? Can you provide an example?
2
votes
0answers
17 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 ...
2
votes
0answers
23 views

How can I train a Deep Learning model using degraded photos and their clean version to correct photos

I have 5000 degraded pictures ( pixelated, blurry, too much luminosity ... ) and their clean versions, and I would like to train a model so that it can predict how to correct future pictures. I've ...
0
votes
1answer
46 views

What AI designs are suited for producing title replacements?

Problem: "For a given news article, generate another title for the article if the article is to be published under a different Publication." Which algorithm will be well suited for this? Should I use ...
0
votes
2answers
141 views

Why am I getting spikes in the values of the loss function during training?

I trained a neural network on the UNSW-NB15 dataset, but, during training, I am getting spikes in the loss function. The algorithms see part of this UNSW dataset a single time. The loss function is ...
0
votes
0answers
19 views

How do I save an Ensemble Learning model? [closed]

I need to save it to my PC so that I can run it with a simple .load() function if something disconnects on the platform I'm using (Google Colab). For demonstration purposes, I just want to load the ...
4
votes
1answer
91 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
3answers
137 views

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

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 ...
2
votes
1answer
55 views

Using ML to analyze Facebook posts

First of all, I should mention that I have a very basic knowledge of ML so I apologize if this question seems trivial or stupid. I am working on a small personal project, basically an app that ...
1
vote
1answer
56 views

Interpretation of feature selection based on the model

The description of feature selection based on a random forest uses trees without pruning. Do I need to use tree pruning? The thing is, if I don't cut the trees, the forest will retrain. Below in the ...
1
vote
0answers
14 views

A problem about the relation between 1-oracle and 2-oracle PAC model

This problem is about two-oracle variant of the PAC model. Assume that positive and negative examples are now drawn from two separate distributions $\mathcal{D}_{+}$ and $\mathcal{D}_{-} .$ For an ...
2
votes
0answers
27 views

How can we prove this inequality, related to the generalization error, without using the Rademacher complexity?

This is an inequality on page 36 of the book Foundations of Machine Learning, but the author only states it without proof. $$ \mathbb{P}\left[\left|R(h)-\widehat{R}_{S}(h)\right|>\epsilon\right] \...
2
votes
0answers
16 views

Convert a PAC-learning algorithm into another one which requires no knowledge of the parameter

This is part of the exercise 2.13 in the book Foundations of Machine Learning (page 28). You can refer to chapter 2 for the notations. Consider a family of concept classes $\left\{\mathcal{C}_{s}\...
2
votes
0answers
19 views

How does the weight update formula for logistic regression work?

I am trying to use Logistic Regression to make a spam filter, but I am having trouble understanding the weight update part. I have processed my email dataset, and I have an attribute vector of the top ...
2
votes
2answers
87 views

Why are traditional ML models still used over deep neural networks?

I'm still on my first steps in the Data Science field. I played with some DL frameworks, like TensorFlow (pure) and Keras (on top) before, and know a little bit of some "classic machine learning" ...
1
vote
0answers
18 views

Is there any paper that uses truncated neural networks?

Recently, I've found good success in truncated neural networks ie functions of the form $$ g=f1_{[-M,M]^d}, $$ where $f:\mathbb{R}^d\to\mathbb{R}^n$ is a feed-forward neural network and $1_{[-M,M]^d}$ ...
2
votes
2answers
572 views

How to perform neural network with output constraint?

Imagine a "simple" feedforward, fully connected neural network, with some input size, some number of hidden layers, and some # of neurons....etc BUT with a fixed number of output size (that is saying, ...
1
vote
0answers
16 views

Training dataset for convolutional neural network classification - will images captured on the ground be useful for training aerial imagery?

I am an agronomy graduate student looking to classify crops from weeds using convolutional neural networks (CNNs). The basic idea that I am wanting to get into involves separating crops from weeds ...
0
votes
1answer
32 views

Isolate the speech of two people in an audio record with two people only

I would like to find a way to isolate the speech of each of the people in an audio record so I can create a file of that form : ...
1
vote
1answer
16 views

Deep audio fingerprinting for word search

Simply speaking, I'm trying to somehow search an audio clip for a list of words, and if found, I mark the time stamps. My use-case is profanity check with a list of pre-defined profane words. Is ...
3
votes
0answers
68 views

Which Rosenblatt's paper describes Rosenblatt's perceptron training algorithm?

I struggle to find Rosenblatt's perceptron training algorithm in any of his publications from 1957 - 1961, namely: Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms The ...
3
votes
1answer
74 views

Why is the average reward plot for my reinforcement learning agent different than the usual plots?

I'm building an RL agent using SARSA and Q-Learning for testing its capabilities. The environment is a 10x10 grid, where it gets a reward of 1 if he reaches the goal while he takes -1 every time he ...
1
vote
0answers
26 views

How can I match numbers with expressions?

Let's say I have the number 123.45 and the expression one hundred twenty-three and forty-five cents. Can I develop AI to identify these two values as a match? If I can, how should I do that?
6
votes
1answer
447 views

What is the formula for the momentum and Adam optimisers?

In the gradient descent algorithm, the formula to update the weight $w$, which has $g$ as the partial gradient of the loss function with respect to it, is: $$w\ -= r \times g$$ where $r$ is the ...
2
votes
0answers
49 views

Suggestion for finding the stable regions in spiral galaxy data?

I am working with a data set that consists of the actual pitch angle (given as PA(Y)) and the pitch angle at each radii (listed from 1 to 217). In the image below, ...
2
votes
1answer
58 views

Why is the entire area of a join probability distribution considered when it comes to calculating misclassification?

In the image given below, I do not understand a few things 1) Why is an entire area colored to signify misclassification? For the given decision boundary, only the points between $x_0$ and the ...
2
votes
2answers
99 views

Can a neural network be used to predict a sequence of integers based on dataset of previously produced random numbers?

What i really want to do, is to predict an integer sequence of (5 numbers with values from 1 to 50) for example based on a big dataset of other 5 numbers sequences with same values range created by ...
2
votes
0answers
48 views

Why isn't there a model playing FPS like CoD or Battlefield already existing?

Assuming we had an unlimited time to train a model and a very powerful machine to use our model in real-time (hello quantum computer), I'd like to know why no one could achieve to build an AI able to ...
0
votes
0answers
30 views

How to Layer based Feature extraction?

I have read that in deep networks you can engineer each layer for a particular purpose with regards to feature learning. I'm wondering how that is actually done and how it is trained? In addition ...
4
votes
1answer
38 views

Can a deep neural network be trained to classify an integer N1 as being divisible by another integer N2?

So I’ve been working on my own little dynamic architecture for a deep neural network (any number of hidden layers with any number of nodes in every layer) and got it solving the XOR problem ...
14
votes
5answers
24k views

Why does C++ seem less widely used in AI?

I just want to know why do Machine Learning engineers and AI programmers use languages like python to perform AI task and not C++ even though C++ is technically a more powerful language than python.