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
25
votes
4answers
8k views

How to handle invalid moves in reinforcement learning?

I want to create an AI which can play five-in-a-row/gomoku. As I mentioned in the title, I want to use reinforcement learning for this. I use policy gradient method, namely REINFORCE, with baseline. ...
21
votes
7answers
2k views

If digital values are mere estimates, why not return to analog for AI?

The impetus behind the twentieth century transition from analog to digital circuitry was driven by the desire for greater accuracy and lower noise. Now we are developing software where results are ...
55
votes
10answers
34k 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 ...
32
votes
3answers
20k views

Why is Lisp such a good language for AI?

I've heard before from computer scientists and from researchers in the area of AI that that Lisp is a good language for research and development in artificial intelligence. Does this still apply, with ...
2
votes
1answer
493 views

Is back propagation applied for each data point or for a batch of data points?

I am new to deep learning and trying to understand the concept of back propagation. I have a doubt on when the back propagation is applied. Assume that I have a training data set of 1000 images for ...
22
votes
5answers
16k 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 ...
47
votes
4answers
11k views

Are neural networks prone to catastrophic forgetting?

Imagine you show a neural network a picture of a lion 100 times and label with "dangerous", so it learns that lions are dangerous. Now imagine that previously you have shown it millions of images of ...
37
votes
3answers
29k views

What is self-supervised learning in machine learning?

What is self-supervised learning in machine learning? How is it different from supervised learning?
84
votes
14answers
13k views

What is the difference between artificial intelligence and machine learning?

These two terms seem to be related, especially in their application in computer science and software engineering. Is one a subset of another? Is one a tool used to build a system for the other? ...
30
votes
9answers
5k views

Is artificial intelligence vulnerable to hacking?

The paper The Limitations of Deep Learning in Adversarial Settings explores how neural networks might be corrupted by an attacker who can manipulate the data set that the neural network trains with. ...
15
votes
3answers
6k views

How to choose an activation function?

I choose the activation function for the output layer depending on the output that I need and the properties of the activation function that I know. For example, I choose the sigmoid function when I'm ...
12
votes
3answers
470 views

How would an AI learn language?

I was think about AIs and how they would work, when I realised that I couldn't think of a way that an AI could be taught language. A child tends to learn language through associations of language and ...
11
votes
4answers
2k views

What are the purposes of autoencoders?

Autoencoders are neural networks that learn a compressed representation of the input in order to later reconstruct it, so they can be used for dimensionality reduction. They are composed of an encoder ...
5
votes
3answers
640 views

What is the actual learning algorithm: back-propagation or gradient descent?

What is the actual learning algorithm: back-propagation or gradient descent (or, in general, the optimization algorithm)? I am reading through chapter 8 of Parallel Distributed Processing hand book ...
59
votes
3answers
38k views

How can neural networks deal with varying input sizes?

As far as I can tell, neural networks have a fixed number of neurons in the input layer. If neural networks are used in a context like NLP, sentences or blocks of text of varying sizes are fed to a ...
39
votes
4answers
57k views

How to select number of hidden layers and number of memory cells in an LSTM?

I am trying to find some existing research on how to select the number of hidden layers and the size of these of an LSTM-based RNN. Is there an article where this problem is being investigated, i.e., ...
18
votes
5answers
19k views

Can a neural network be used to predict the next pseudo random number?

Is it possible to feed a neural network the output from a random number generator and expect it learn the hashing (or generator) function, so that it can predict what will be the next generated pseudo-...
28
votes
2answers
1k views

How is a deep neural network different from other neural networks?

How is a neural network having the "deep" adjective actually distinguished from other similar networks?
5
votes
2answers
2k views

Are neural networks statistical models?

By reading the abstract of Neural Networks and Statistical Models paper it would seem that ANNs are statistical models. In contrast Machine Learning is not just glorified Statistics. I am looking ...
10
votes
1answer
577 views

What are the implications of the “No Free Lunch” theorem for machine learning?

The No Free Lunch (NFL) theorem states (see the paper Coevolutionary Free Lunches by David H. Wolpert and William G. Macready) any two algorithms are equivalent when their performance is averaged ...
7
votes
2answers
1k views

Why exactly do neural networks require i.i.d. data?

In reinforcement learning, in general, successive states (actions and rewards) are highly correlated. An "experience replay" buffer was used, in the DQN architecture, to avoid training the neural ...
11
votes
3answers
420 views

What are the main problems hindering current AI development?

I have a background in Computer Engineering and have been working on developing better algorithms to mimic human thought. (One of my favorites is Analogical Modeling as applied to language processing ...
10
votes
1answer
1k views

Mathematical intuition for the use of Re-Lu's in Machine Learning

So, currently the most commonly used activation functions are Re-Lu's. So I answered this question What is the purpose of an activation function in Neural Networks? and while writing the answer it ...
4
votes
2answers
228 views

How to estimate the capacity of a neural network?

Is it possible to estimate the capacity of a neural network model? If so, what are the techniques involved?
4
votes
1answer
510 views

How does an unsupervised learning model learn?

How does an unsupervised learning model learn, if it does not involve any target values?
3
votes
1answer
141 views

Use cross-validation to train after model selection

I have been recently reading about model selection algorithms (for example to decide which value of the regularisation parameter or what size of a neural network to use, broadly hyper-parameters). ...
1
vote
1answer
69 views

What is a fully convolution network?

I was surveying some literature related to Fully Convolutional Networks and came across the following phrase, A fully convolutional network is achieved by replacing the parameter-rich fully ...
24
votes
2answers
10k views

Is it possible to train a neural network incrementally?

I would like to train a neural network where the output classes are not (all) defined from the start. More and more classes will be introduced later based on incoming data. This means that, every time ...
15
votes
2answers
1k views

When is deep learning overkill?

For example, for classifying emails as spam, is it worthwhile - from a time/accuracy perspective - to apply deep learning (if possible) instead of another machine learning algorithm? Will deep ...
11
votes
1answer
372 views

How to stay a up-to-date researcher in ML/RL community?

As a student who wants to work on machine learning, I would like to know how it is possible to start my studies and how to follow it to stay up-to-date. For example, I am willing to work on RL and MAB ...
19
votes
3answers
24k views

Understanding GAN loss function

I'm struggling to understand the GAN loss function as provided in Understanding Generative Adversarial Networks (a blog post written by Daniel Seita). In the standard cross-entropy loss, we have an ...
9
votes
4answers
1k views

What do I need to study for machine learning?

Starting from last year, I have been studying various subjects in order to understand some of the most important thesis of machine learning like S. Hochreiter, & J. Schmidhuber. (1997). Long ...
6
votes
3answers
4k views

What is non-Euclidean data?

What is non-Euclidean data? Where does this type of data arises? Apparently, graphs and manifolds are non-Euclidean data. Why exactly is that the case? What is the difference between non-Euclidean and ...
10
votes
3answers
14k views

Measuring Object size using Deep Neural Network

I have a large dataset of vehicles with the ground truth of their lengths (Over 100k samples). Is it possible to train a deep network to measure/estimate vehicle length ? I haven't seen any papers ...
4
votes
1answer
420 views

Reinforcement Learning in asteroid game

Introduction An attractive asteroid game was described in the paper from 2007: quote: “In our first experiment, the virtual agent is a spaceship pilot, The pilot’s task is to maneuver the ...
9
votes
1answer
2k views

Selecting the right technique to predict disease from symptoms

I'm trying to come up with the right algorithm for a system in which the user enters a few symptoms and the system has to predict or determine the likelihood that a few selected symptoms are ...
8
votes
2answers
5k views

How do we choose the kernel size depending on the problem?

Obviously, finding suitable hyper-parameters for a neural network is a complex task and problem or domain-specific. However, there should be at least some "rules" that hold most times for the size of ...
7
votes
3answers
733 views

How can I start learning mathematics for machine learning?

I am an Android programmer. Now, I would like to learn machine learning. I know it requires a mathematical background, like statistics, probability, calculus and linear algebra. However, I am a bit ...
5
votes
4answers
387 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 ...
4
votes
1answer
74 views

Is it possible to combine two neural networks trained on different tasks into one that knows both tasks?

I'm relatively new to artificial intelligence and neural networks. Let's say I have two different fully trained neural networks. The first one is trained for mathematical addition and the second one ...
4
votes
2answers
115 views

Mathematical foundations of the ability to learn

I am an undergraduate student in applied mathematics with an interest in artificial intelligence. I am currently exploring topics where I could do research. Coming from a mathematical background I am ...
4
votes
3answers
210 views

What kinds of problems can AI solve without using a deep neural network?

A lot of questions on this site seem to be asking "can I use X to solve Y?", where X is usually a deep neural network, and Y is often something already addressed by other areas of AI that are less ...
4
votes
3answers
264 views

Can someone direct me to a sites and/or videos that can bring an absolute beginner up to speed with AI?

To start, I'm not a programmer/computer scientist/et al... - I work in Finance and have, through my job, self-thought myself VBA for excel and outlook and would consider myself as being in the upper ...
3
votes
3answers
466 views

Which functions can't neural networks learn efficiently?

There are a lot of papers that show that neural networks can approximate a wide variety of functions. However, I can't find papers that show the limitations of NNs. What are the limitations of ...
2
votes
2answers
1k views

What's the role of bounding boxes in object detection?

I'm quite new to the field of computer vision and was wondering what are the purposes of having the boundary boxes in object detection. Obviously, it shows where the detected object is, and using a ...
2
votes
1answer
42 views

Should I remove the units of a neural network or increase dropout?

When adding dropout to a neural network, we are randomly removing a fraction of the connections (setting those weights to zero for that specific weight update iteration). If the dropout probability is ...
2
votes
3answers
519 views

Is there such a thing like the machine learning paradox?

O'Reilly recently published an article about the machine learning paradox. (link) What it says goes basically like this: no machine learning algorithm can be perfect. If it was, it means it is ...
1
vote
1answer
290 views

How do I restrict the neural network structure to be acyclic in NEAT?

I want my neural network structure to not have a circular/looping structure something similar like a directed acyclic graph (DAG). How do I do that?
10
votes
3answers
219 views

What is a deep neural network?

What is the definition of a deep neural network? Why are they so popular or important?
9
votes
3answers
637 views

Does Monte Carlo tree search qualify as machine learning?

To the best of my understanding, the Monte Carlo tree search (MCTS) algorithm is an alternative to minimax for searching a tree of nodes. It works by choosing a move (generally, the one with the ...