17
votes
Accepted
What is meant by the term "prior" in machine learning
Put simply, and without any mathematical symbols, prior means initial beliefs about an event in terms of probability distribution. You then set up an experiment and get some data, and then "update" ...
- 9,727
11
votes
Accepted
Normalized measure from dynamic time warping
Sure. There's a straightforward way to convert an unnormalized distance metric into a normalized similarity measure. Basically, use
$$S(x,y) = \frac{M - D(x,y)}{M},$$
where $D(x,y)$ is the ...
D.W.♦
- 154k
6
votes
Accepted
Partial polygon matching
There is quite a bit of work on this important problem. Some of the most
insightful work is by Helmut Alt and collaborators. He wrote a survey in 2009:
Helmut Alt. "The computational geometry of ...
- 854
4
votes
Accepted
What is a good approach to symbol identification/recognition given a path, instead of raster data
What you are looking for is called "on-line recognition". I have written my Bachelors thesis about this:
Thoma, Martin. "On-line Recognition of Handwritten Mathematical Symbols." arXiv preprint ...
- 2,350
4
votes
Accepted
What method of collective recogintion to use for digits recognition?
The state of the art for digit recognition does not use collective recognition, competence areas, ensembles, or any of the other ideas you propose in your question.
Instead, the state of the art for ...
D.W.♦
- 154k
3
votes
Accepted
Which algorithm for counting the occurrences of a certain pattern (spots) in an image?
The best way to get an orientation is to read a textbook on computer vision or image processing. There are lots of techniques known, and that's often the best way to get an introduction to a broad ...
D.W.♦
- 154k
3
votes
Machine Learning: Identify Patterns in Time-Series Data
Yes, your data is "time-series data", since it's a sequence of measurements of the same variable collected over time. Time-series data can be collected continuously or at discrete intervals.
Your ...
- 1,604
3
votes
How are Neural Networks made so general?
Neural nets don't "understand", they are trained. Despite the fancy term, a neural net is simple a regression model on steroid - often high-dimensional. It's a bunch of weights (vectors) connected in ...
- 131
3
votes
Accepted
Multi object image segmentation methods
I think that you are interested in MFC - Multiple Foreground Cosegmentation.
MFC article
Awesome material:
Articulated Motion and Deformable Objects : 5th International Conference, AMDO 2008, Port d'...
- 9,385
3
votes
Extracting features for texture classification
If it is important for you to get a high accuracy, then use a convolutional neural network (ConvNet). These ConvNets hold the state of the art for most visual recognition tasks. If your training set ...
- 131
3
votes
Accepted
How does continuous computer vision works?
It depends on what you're recognizing, but I'm familiar with two basic techniques:
Apply the recognition algorithm to each frame of the video. Be fast enough that you can run on every frame of video....
D.W.♦
- 154k
2
votes
Automated lip-reading: inferring what someone is saying, based upon video of them speaking
There is some recent work here:
LipNet: Sentence-Level Lipreading. Yannis M. Assael, Brendan Shillingford, Shimon Whiteson, and Nando de Freitas.
They achieve 93% accuracy on a corpus of 3-second ...
D.W.♦
- 154k
2
votes
Partial polygon matching
One reasonable approach is to use RANSAC to find a homography that causes many points to be aligned (or approximately aligned). You'd apply this procedure to align the set of vertices of the first ...
D.W.♦
- 154k
2
votes
Accepted
Efficiently find smallest unique substring
You can try suffix array approach which find all suffix of a given string of length n in O(n) time.
There are many algorithm to construct suffix array from a given input string.
Look at complete ...
- 119
2
votes
How are Neural Networks made so general?
there is some deep academic research on AI/Machine Learning applied crossword solvers, eg contained in the following paper. the basic effective systems utilize large databases of clue-answer pairs ...
- 11k
2
votes
Accepted
deterministic finite automaton for "does contain substring $w$" is of linear size
Consider the following NFA: the states are $q_0,\ldots,q_{|w|}$, there are transitions $q_{i-1} \to q_i$ on $w_i$, there are self-loops on $q_0,q_{|w|}$ (for all alphabet symbols), the initial state ...
- 274k
2
votes
Accepted
Where I can I find Pre Trained CNN Datasets for Facial Emotion Recognition?
You are probably interested in IAPS, and want to read Analysis of Physiological Signals for Emotion Recognition Based on Support Vector Machine.
But to be honest this classification is doomed in ...
- 9,385
2
votes
Accepted
how to identify patterns in program execution flows?
There's probably no existing turnkey solution that will do what you want, out of the box. I suspect this would be a research-level task, so you might want to start by searching the research ...
D.W.♦
- 154k
2
votes
Accepted
Finding (and possibly extracting) source code in heterogenous text data set
There are many possible ways you might do this. I'll suggest one.
I suggest you train a classifier to recognize whether a sequence of characters is code or text. Here, the goal is to build a ...
D.W.♦
- 154k
2
votes
Accepted
reverse string to pattern matching
The Shortest Levenshtein's Distance should be good enough.
See if this Matching Wildcards Wikipedia page can be of help.
2
votes
Recognizing a trajectory from a set
The Fréchet distance is a similarity measure for trajectories that often works well for curves that we consider visually similar. However, it is not scale or translation invariant, because it compares ...
- 7,768
2
votes
A pretrained model for mathematical equations characters detection
Detexify is a service that recognizes LaTeX symbols from handwritten figures. Their training dataset is freely available on Github.
- 7,768
2
votes
Accepted
Can computer vision process 3D “images” directly?
This is a very general question, so I'll give some ideas.
The short answer is yes. If you're talking about the "processing" as some function, then yes, we can use some function $f_3: \mathbb{...
- 352
1
vote
What is meant by the term "prior" in machine learning
In Bayesian statistics, a "prior" represents the beliefs we have before observing some data. Then, after we observe some data, we update our beliefs; those updated beliefs are called the &...
D.W.♦
- 154k
1
vote
What is meant by the term "prior" in machine learning
It's roughly any pre-training choices you encode into your model
In machine learning a prior is, according to the book "Deep Learning" by Goodfellow, Bengio, and Courville, a probability ...
- 111
1
vote
Changing Rabin-Karp without modulo to Rabin-Karp with modulo
Don't wait to do the modular reduction at the end. Every time you do an addition or multiplication, immediately reduce modulo the modulus. This keeps all intermediate results small.
D.W.♦
- 154k
1
vote
Accepted
Simple Recognition Algorithm, How Does It Work?
Normally we build a classifier that accepts images of a fixed size: say, 100x100 pixels. Given an image that is larger than that, we re-scale it to 100x100 pixels before feeding it into the ...
D.W.♦
- 154k
1
vote
What are the pros and cons of RANSAC versus Hough Transform?
The Hough transform would be a reasonable approach for this. Another reasonable approach would be to find connected regions of similar hue, and for each, test if it is approximately pool-ball-shaped.
...
D.W.♦
- 154k
1
vote
Find string patterns preferably in regex for string streams
The general approach is likely to be:
Identify a set of candidate patterns that might appear.
For each candidate pattern, check for all instances of that pattern.
I'm not aware of any simple ...
D.W.♦
- 154k
1
vote
Getting speed difference between signal comparison using Dynamic Time Warping
DTW is designed to handling local changes in timing.
Global changes is time are referred to as Uniform Scaling [a].
You can create a FOR loop, loop over all possible Uniform Scalings, and record ...
- 11
Only top scored, non community-wiki answers of a minimum length are eligible