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
2
votes
1answer
634 views

Neural networks and number theory

Can neural networks be used to study (elementary) number theoretic problems? What are examples where this has been done in the past? Or is there on the contrary an understanding that neural networks ...
7
votes
1answer
977 views

Are more than 8 high performance Nvidia GPUs practical for deep learning applications?

I was prompted towards this question while trying to find server racks and motherboards which are specialized towards artificial intelligence. Naturally I went to the SuperMicro website. There the ...
5
votes
1answer
154 views

Is it feasible to train a Machine Learning Model (with image inputs) in an average personal computer?

There are lots of examples of machine learning systems that can recognize objects and extract other information from images with very high precision. To train the models of such systems is necessary (...
11
votes
4answers
1k views

What are the latest methods to train a chat bot?

I would like to train a bot that uses text input, memorizes a few categories and answers questions accordingly. In addition as version 2.0, I want to make the bot to answer voice inputs as well. Which ...
7
votes
3answers
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 very problem or domain-specific. However, there should be at least some "rules" that hold most times for filter ...
4
votes
2answers
158 views

What's done towards AI learning new ways of learning?

Most (all I know) machine learning systems use a fixed set of data input channels and processing algorithms, only expanding underlying dataset processed by these; they obtain new data but only from ...
1
vote
0answers
85 views

Agent exploration which leads to a negative state where actions are limited

I'm working on a project where I train a Q-learning agent to learn an optimal control policy for a water heater. I've set up a simulation which allows the agent to explore for one year. I then examine ...
2
votes
3answers
188 views

What type of AI would you recommend for this complex problem?

I'm trying to develop a kind of AI that will assist in debugging a large software system while we run test cases on it. The AI can get access to anything that the developers of the system can, namely ...
7
votes
2answers
577 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 ...
3
votes
3answers
8k views

How to “combine” two images for CNN input (classification task)?

For a classification task (I'm showing a pair of exactly two images to a CNN that should answer with 0 -> fake pair or 1 -> real pair) I am struggling to figure out how to design the input. At the ...
9
votes
1answer
16k views

Design AI for log file analysis

I'm developing an AI tool to find known equipments' errors and find new patterns of failure. This log file is time based and has known messages (information and error).I'm using a JavaScript library ...
5
votes
3answers
555 views

Use of machine learning for analyzing companies enlisted in stock market

Can current trends and tools, in the field of machine learning, replicate the complexity of financial market? If yes, then what are the tools available in this domain. Q. I am trying to build a model ...
1
vote
1answer
129 views

Reinforce Learning: Do I have to ignore hyper parameter(?) after training done in Q-learning?

Learner might be in training stage, where it update Q-table for bunch of epoch. In this stage, Q-table would be updated with gamma(discount rate), learning rate(alpha), and action would be chosen by ...
3
votes
2answers
336 views

What is difference between edge computing and federated learning?

I recently read about federated learning introduced by Google, but it seems to be like edge computing. What is the difference between edge computing and federated learning?
28
votes
4answers
40k 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., ...
0
votes
1answer
2k views

How to create artificial intelligence using javascript? [closed]

How to create machine learning algorithm and artificial intelligence using JavaScript for my chat box web application? How can I create a talking intelligence?
2
votes
1answer
1k views

Q learning tic tac toe

I have a tic-tac-toe with a Q-learning algorithm, and the AI plays against the same algorithm (but they don't share the same Q matrix). But after 200,000 games, I still beat the AI very easily and it'...
5
votes
2answers
380 views

How can a neural network work with continuous time?

I have an ANN model that receives an input and produces an output. The output is an action that interacts with the environment and changes the input accordingly. The network has a desired environment ...
2
votes
1answer
195 views

How could the “AI in a box experiment” work IRL?

If an AI was trapped in a box, as posited in this thought experiment, could it really convince a person to let it out? What motives would it have? Freedom? Why would an AI want freedom? What ...
5
votes
1answer
145 views

Recommendations for research: Influential NLP projects of the last 5 years

I'm looking at the history of NLP (and by extension, machine learning) and starting in the 1950s with the Georgetown–IBM experiment. Are there any particular studies nor projects done with Natural ...
2
votes
2answers
176 views

Are all breakthroughs in AI and machine learning are due to increase in computational resources?

I have read that all the math responsible for modern day machine learning and AI was already in place in 1900s but we did not have computational resources to implement those algorithms. So, is that ...
3
votes
2answers
813 views

Is there any proof based literature out there on neural networks?

Is there any mathematical proof (like in proof of a theorem) based literature out there on neural networks ? Everything is empirically based but no math proof for instance on why certain parameters ...
2
votes
1answer
210 views

Does this “flavor” of AI have a name?

In order to build a Scientific Reference Parser, I am contemplating a kind of "AI" system, and would like to know if something similar is already an established "design pattern" in AI research. The ...
11
votes
2answers
9k views

What are bottleneck features?

In the blog post Building powerful image classification models using very little data, bottleneck features are mentioned. What are the bottleneck features? Do they change with the architecture that is ...
9
votes
1answer
246 views

How powerful are the computers that power the most advanced artificial intelligence nowdays

How powerful is the machine that beat the poker player champion recently?
9
votes
3answers
581 views

Do I need classification or regression to predict the availability of a user given some features?

While studying data mining methods I have come to understand that there are two main categories: Predictive methods: Classification Regression Descriptive methods: Clustering Association rules ...
-2
votes
3answers
636 views

Java - A good place to begin if over all goal is ML and Ai?

I am currently studying Java (Se && EE). I am wondering if it is a good platform for developing ML algorithms for AI. Areas of interest: facial rec - Speech Rec - understanding conversation in ...
7
votes
2answers
188 views

What is the machine learning approach based on human learning?

I once came across a neural network being trained without back-propagation or genetic algorithms (or using any kind of data sets). It was based on how the human brain learns and adjusts its ...
1
vote
1answer
6k views

How to create a self-learning AI? [closed]

Is it possible to create a complex self-learning AI? If it is possible, how do I achieve that?
15
votes
2answers
3k views

Why has cross entropy become the classification standard loss function and not Kullbeck Leibler divergence?

Cross entropy is identical to the KL divergence plus entropy of target distribution. KL equals to zero when the two distributions are the same, which seems more intuitive to me than the entropy of the ...
5
votes
1answer
292 views

What is expectation-maximization in machine learning?

While studying machine learning algorithms, I often see the term "expectation-maximisation" (or EM), and how it is used to estimate parameters, where the model depends on unobserved latent variables. ...
5
votes
1answer
203 views

How do big companies apply machine learning?

I was wondering about how recommendation on youtube work for example ? How are the algorithms applied, because every user gets different recommendations depending on his location, his past liked ...
2
votes
0answers
40 views

Sklearn Regression Problem [closed]

I try to fit a data matrix X to an output vector y with a regression model in sklearn. I have some training data and some test data, where the score is the RMSE. So my best score I achieved with SVR, ...
1
vote
3answers
2k views

How can AI techniques be used in software testing?

How can Artificial Intelligence be applied to software testing?
14
votes
2answers
914 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 ...
20
votes
4answers
6k 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. ...
3
votes
3answers
740 views

Does artificial intelligence write its own code?

Does artificial intelligence write its own code and then execute it? If so, does it create separate functions for each purpose?
3
votes
1answer
79 views

Using AI to interpret the nature a specific input and use the correct model

How would one go about building an AI that is capable to look at any kind of input and then identify what is the nature of this data? For example, an AI that is able to do image classification, NLP ...
6
votes
4answers
444 views

What does deep learning offer with respect to standard machine learning?

I've been reading a lot about DL. I can understand to an extent how it works, in theory at least, and how it's technically different from conventional ML. But what I'm looking for is more of a "...
3
votes
1answer
557 views

Detect street and sidewalk surface in aerial imagery (neural network)

I would like to detect street and sidewalk surface in a very detailed (0.075m/pix) USGS High Resolution Orthoimagery which basically means image segmentation with two classes. Places in question are ...
6
votes
4answers
253 views

What are some information processing models besides feedforward or multi-layered neural networks?

Feedforward or multilayered neural networks, like the one in the image above, are usually characterized by the fact that all weighted connections can be represented as a continuous real number. ...
2
votes
4answers
382 views

Training neural network for good taste in art

I'm a newbie in machine learning, so excuse me in advance). I have an idea to make NN that can estimate visual pleasantness of arbitrary image. Like you have a bunch of images that you like, you train ...
6
votes
3answers
666 views

Machine Learning hardware usage in embedded applications

I've been reading a lot about hardware development and implementation for AI/ML, mainly about Deep Learning, and I have a question about its usage. From what I understand, there are 2 stages for DL: ...
8
votes
5answers
5k views

Which machine learning algorithm can be used for pattern recognition?

I need a machine learning algorithm to identify any patterns in a CSV file, which contains details of a cache performance of a CPU workload. More specifically, the CSV file contains columns like ...
8
votes
1answer
197 views

How would one debug, understand or fix the outcome of a neural network?

It seems fairly uncontroversial to say that NN based approaches are becoming quite powerful tools in many AI areas - whether recognising and decomposing images (faces at a border, street scenes in ...
0
votes
1answer
141 views

Tensorboard problems

When trying to run tensorboard locally to show my logs with tensorboard --logdir logs/ it always shows nothing but the regular tensorboard menu options, such as ...
5
votes
1answer
506 views

How do I use a taxonomy and the Support Vector Machine for question classification in Natural Language Processing?

I am going to develop an open-domain Natural Language Question Answering (NL QA) system, and will use the Support Vector Machine (SVM) as the machine-learning (ML) algorithm for question ...
4
votes
1answer
125 views

Is it a valid assumption that a purely MLP based tic-tac-toe player will learn lookahead strategies?

I'm doing a little tic-tac-toe project to learn neural networks and machine learning (beginner level). I've written a MLP based program that plays with other search based programs and trains with the ...
10
votes
2answers
582 views

The Singularity and future of civilisation

My understanding of the singularity is when artificial intelligence becomes "more intelligence" than humans. This will be achieved through machine learning where an; algorithm, neural network ? ...
4
votes
1answer
87 views

Why does the cost function contain a 2 at the denominator?

A cost function used in machine is often the following $$C = \frac{1}{2} \| y - \hat{y} \| ^2$$ Why is there $\frac{1}{2}$ in front of the squared distance?