relates to algorithms that are "trained" by some data set.

learn more… | top users | synonyms

134
votes
14answers
7k views

Simple method for reliably detecting code in text?

GMail has this feature where it will warn you if you try to send an email that it thinks might have an attachment. Because GMail detected the string see the attached in the email, but no actual ...
11
votes
4answers
17k views

Industry jobs in artificial intelligence [closed]

As a relatively new computer science student, I am trying to find my niche within this broader field. My main goal is not academia but, well, a job. As such, I want to choose a specialization or two ...
11
votes
9answers
916 views

Learning the rules of chess

A similar question asks whether a computer can learn to play optimally in chess by analyzing thousands of games. If a machine can look at the state of the board for a few games of chess (or a few ...
11
votes
3answers
3k views

Switching to a career in Machine Learning [closed]

My day job is plain old software development. I am also doing my Masters in CS (part time, course based). I took a course on AI and found machine learning quite fascinating but like most courses it ...
11
votes
1answer
2k views

How is machine learning incorporated into search engine design?

I am currently building a small in-house search engine based on Apache Lucene. Its purpose is simple - based on some keywords, it will suggest some articles written internally within our company. I am ...
10
votes
4answers
637 views

Using machine learning to aim mirrors in a solar array?

I've been thinking about solar collectors where several independent mirrors to focus the light on a solar collector, similar to the following design from Energy Innovations. Because there will be ...
10
votes
5answers
2k views

Is it imaginable to teach a machine how to program itself to a defined specification? [closed]

A friend of mine without programming knowledge asked me this question and I found it interesting. I think it is not possible because it would require a really advanced artificial intelligence ...
10
votes
3answers
1k views

Can a neural network provide more than “yes” or “no” answers?

Every example neural network for image recognition I've read about produces a simple "yes" or "no" answer. One exit node corresponds to "Yes, this is a human face," and one corresponds to "No, this ...
10
votes
1answer
8k views

Decision trees vs. Neural Networks

I'm implementing a machine learning structure to try and predict fraud on financial systems like banks, etc... This means that there is a lot of different data that can be used to train the model eg. ...
9
votes
5answers
9k views

What's the best way to learn image processing? [closed]

I'm a senior in college that hasn't done much image processing before (except for some basic image compression on smartphones). I'm starting a research project on machine learning next semester that ...
8
votes
2answers
3k views

What math skills are required to learn machine learning? [closed]

I am interested in taking this online course on machine learning. As it stands my math is very elementary, and I am basically learning math from scratch on khan academy. Programming-wise I have a ...
8
votes
1answer
458 views

what do programmers dealing with data driven/machine learning related programming need? [closed]

Given the increasing amount of data generated through different web services ( social network, etc), there are must be more and more programmers who are familiar with machine learning and/or ...
7
votes
3answers
3k views

What algorithm(s) can be used to achieve reasonably good next word prediction?

What is a good way of implementing "next-word prediction"? For example, the user types "I am" and the system suggests "a" and "not" (or possibly others) as the next word. I am aware of a method that ...
7
votes
2answers
3k views

Machine Learning With Categorical and Continuous Data

This question could go here or on S.O. perhaps... Suppose that your training dataset contains both categorical and continuous data such as this setup: Animal, breed, sex, age, weight, ...
6
votes
5answers
7k views

What skills are needed for machine learning jobs? [closed]

I posted this question on Quora, but didn't get enough responses. reposting it here. I am a learner sitting at home and learning linear algebra, very interested on working in Machine Learning ...
6
votes
2answers
715 views

How to trim emails for just the body, when using email as input to an external system?

When an application allows emails to be sent to it to either reply to comments or add todos, trimming those emails for just the relevant text becomes a problem, since there are many different ...
6
votes
1answer
513 views

Using grammars to extract bibliographic citations

My task lays in the area of text mining / labelling, more particular extraction of bibliographic citations (references) from the plain text, as shown here: Basically, for the input text the ...
5
votes
1answer
342 views

What's the normal way machine-learning algorithms are integrated into normal programs?

I'm currently taking a machine learning course for fun, and the course heavily focuses on Matlab/Octave to write the code. One thing mentioned in the course is that, while Matlab/Octave are great for ...
5
votes
1answer
132 views

quantitatively comparing AST shapes

How could one compare the shape of abstract syntax trees of similar source code programs (C, C++, Go, or anything compiled with GCC...)? I guess that plagiarism detection on source code would use ...
5
votes
1answer
146 views

Algorithm for predicting outcome based on parameters

I've never done anything with statistics, so I'm unsure of how to start with this problem that I need to solve for some software that I'm working on. Basically, there are three parameters An ...
5
votes
2answers
328 views

How to solve this problem- Neural Net? Fuzzy? Other?

Hi I have a programming problem that I would like to solve using some artificial intelligence technique. I really dont know where to start. I would like some guidance as to what methodology to pursue. ...
4
votes
4answers
728 views

Implementing a machine learning algorithm to detect the region of an address

I have 10,000 addresses from a city, which all have a region field in the database. When a new address is entered, then I want my software to automatically detect the region of the address . I think ...
4
votes
2answers
1k views

What is the required background to apply Machine Learning to Finance?

I'm interested in machine learning in relations to the stock market (predicting future values of stocks etc). What topics would I need to learn - e.g. what branch of AI to look into etc? and what ...
4
votes
2answers
137 views

Can I use machine learning for screening experimental data?

I am a experimental physicist. In our research, we have our experimental data in a 400*400*400 matrix(x, y, z axis of a 3d space), each entry is associated with a value("brightness"). We expect the ...
4
votes
2answers
324 views

Can symbolic AI 'learn' a data model?

Perceptrons, a simple form of supervised machine learning, must be trained with a set of known good inputs before they can "learn" by adjusting internal weights assigned to inputs, based on the ...
3
votes
1answer
402 views

Watson Information Encoding [closed]

IBM's Watson has a lot of book information encoded into a 'database' that Watson searches in real time. Does anyone know how that information is coded? It seems hard to imagine how humans could type ...
3
votes
1answer
644 views

Machine Learning with sample data set

I have a question regarding Machine Learning in general. Consider the following scenario: Given a piece of text, we want a program to know whether the text is 'abusive' or not. To do this we can ...
3
votes
2answers
3k views

Separating words in a string

How do I separate words in a string? In the following I have a random sample of words in a string extracted from text file with over a million words. Here's the string: "intervene Pockets ...
3
votes
2answers
155 views

Clustering algorithm that doesn't require predefining the number of clusters required

I have a set of user queries from a search engine that I want to cluster. The only clustering algorithm I have come across so far is the K-means clustering algorithm, which requires defining the ...
3
votes
1answer
162 views

Modern approaches to retrieve useful content from a web page?

What are the modern ways to (effectively) determine which part of page contains useful text, data tables, etc. and which are not (e.g. ads, navigation, etc.)? What were the last valuable ...
3
votes
1answer
201 views

Tasks incorrectly categorized with online text classifiers

Context: Finding company to do the job The use case of an application I want to write is that a user will describe a task to be performed by some company, e.g., I want to move 10 boxes ...
3
votes
2answers
148 views

Learning system instead of using sed/replace for reviewing test results

For every build of my software I run it through a series of tests that execute a number of commands on a command line and captures the results. Most of the time the output is a combination of: - ...
3
votes
1answer
71 views

Reward discounting in reinforcement learning

I've been reading the Sutton and Barto book and following David Silver's lectures on youtube. The basic principles make a lot of sense to me and I've been building a maze (an arbitrary grid where the ...
3
votes
1answer
93 views

Clustering algorithm based on distance

So, I have a packaging center A. And I have n points scattered around A. Let's call them i1, i2 ... in. I have a maximum distance threshold, called D. My task is to break those n points into groups ...
2
votes
6answers
414 views

What applications for self-adaptive programs can you think of? [closed]

Hey everyone! By self-adaptive programs, I mean the programs which are able to adapt to specific situations. For example they are able to repair them selves or are able to change their behavior ...
2
votes
1answer
81 views

To what values should you initialize the neurons and connection strengths in a neural network?

The values of all of the neurons in my neural network are initialized to 0 and the connection strengths between the neurons are set to randomly generated floats, between 0 and 1. I have seen other ...
2
votes
1answer
83 views

How can you write an activation function in a neural network to handle a layer architecture of arbitrary dimensions?

I am making a neural network in Clojure that can take an array of integers,and return a data structure representing the layers of a neural network: so (make-layers [1 4 5]) would evaluate to: [[0] ...
2
votes
1answer
140 views

How to access large amounts of data for machine learning in a microservices architecture

Imagine you are building a product recommendation algorithm for an eccommerce application which is built as a microservices architecture, this architecture having separate services for users and ...
2
votes
1answer
188 views

Random forest ML algorithm suitable for use on cluster based HPC?

I need help in identifying a better algorithm. I have developed a script using pythons scipy package to analyse a rather large model that I wish to solve. The model contains over 12GB of data ...
2
votes
1answer
162 views

Support Vector Machines as Neural Nets?

This is more of a conceptual question. I have learned about Neural Nets, and I have some clue as to how Support Vector Machines work. I read somewhere however that given the appropriate kernel (is ...
2
votes
1answer
196 views

What machine learning algorithm[s?] would be applicable here?

I have documents that contain an arbitrary amount of key/value fields. The value can be a primitive or a list. Completed documents all have an associated state (such as passed, failed, halted, etc.). ...
2
votes
0answers
89 views

Predicting package delivery schedules

I'm trying to solve the following problem: A delivery man has N packages to deliver, already sorted. He starts the route at start_time, he works until end_time. I have historical data of his ...
2
votes
0answers
84 views

How do I visualise the feature space partitioning in random forest?

I am learning about random forest and found this video https://www.youtube.com/watch?v=gdnIqGbqiYs&list=UUb9svouAi1XHRqlOs8LXbBg very useful. The first 8 minutes explain how to visualise how the ...
2
votes
0answers
32 views

How to use event weights in TMVA ROOT

I'm trying to train and perform classifiers from TMVA. My data set contains event weights besides event data. In the TMVA::Factory there's a method setWeightExpression to specify event weights. What ...
1
vote
1answer
1k views

How to design a calculator from scratch [closed]

A basic calculator can perform a wide variety of operations. How does the claculator 'get' the concept of adding two numbers in the same way a human does? I dont think people that make claculators ...
1
vote
1answer
747 views

Is Agile Development used in Machine Learning and Natural Language Processing?

I've been developing web apps for a while now and it is standard practice in our team to use agile development techniques and principles to implement the software. Recently, I've also become involved ...
1
vote
1answer
163 views

What does it mean for an algorithm to converge?

I keep coming across this term when reading about reinforcement learning, for example in this sentence: If the problem is modelled with care, some Reinforcement Learning algorithms can converge to ...
1
vote
2answers
1k views

How to create a Semantic Network like wordnet based on Wikipedia?

I am an undergraduate student and I have to create a Semantic Network based on Wikipedia. This Semantic Network would be similar to Wordnet(except for it is based on Wikipedia and is concerned with ...
1
vote
1answer
53 views

How supervised or unsupervised machine learning algorithms get better over new datasets

Using this Coursera's course about machine learning, I learned some things about supervised and unsupervised algorithms. And from Wikipedia I've read that machine learning is "to get better ...
1
vote
1answer
228 views

How can I apply machine learning to automated melody generation? [closed]

I've been working for a while on an app that makes up melodies. Each melody is composed of several phrases (musical sentences, or 'sub-melodies'). Now, I want to improve on this: The user can press ...