6

The following post has a bit of math, which I hope helps to explain the problem better. Unfortunately it seems, this SE site does not support LaTex: Document summarization is very much an open problem in AI research. One way this task is currently handled is called "extractive summarization". The basic strategy is as follows: Split this document into ...


5

To perform image recognition you have to find a way to represent an image with certain features. One of the defining characteristics of a good image recognition algorithm are it's ability to detect salient regions, that is, regions which contain the most information There is a lot of attention on deep learning for content-based image classification at the ...


3

Firstly, before we commence I will recommend that you refer to similar questions on the network i.e. https://stackoverflow.com/questions/6499880/ios-gesture-recognition-utilizing-accelerometer-and-gyroscope and https://stackoverflow.com/questions/6368618/store-orientation-to-an-array-and-compare Your problem can be divided into three parts. How to gather ...


3

Because it is video input and the logos are usually stationary because they are layered over the live or recorded frames by either hardware or software, the task is not difficult. Logos also usually have limited color palettes and crisp edges. The features of their fonts, when they spell words or acronyms are usually consistent too. These are generalities ...


3

Just to add some discourse; this is actually an incredibly complex task, as gestures (aka kinematics) function as an auxiliary language that can completely change the meaning of a sentence or even a single word. I recently did a dissertation on the converse (generating the correct gesture from a specific social context & linguistic cues). The factors ...


2

They may be just for fun. If you had a robot that understood you, could hold a conversation with you about your interests, and even had goals of its own (good or bad), it wouldn't really need to do anything special. People would buy it like it was a toy or game. Also, they might be usable as programmers, artists, designers, anything creative that a computer ...


2

Yes, there is. An extremely quick search found this: Multimodal Speaker Identification Based on Text_and_Speech. Let me tl;dr for you: (My abstract addition in Italics) Novel method for speaker identification based on both speech utterances and their transcribed text. They first transcribed text of each speaker’s is processed by using probabilistic ...


2

Yes, it is possible, even if the best approach could be different from neural networks. Anyway, you should extract some significant features from the audio (energy, onsets, root frequencies, and other). Usually, more features than those really needed are extracted and afterwards the most sigificant are selected through some algorithm (e.g. PCA). In this way ...


2

What you described sounds to me like Optical Character Recognition(OCR). If you want to implement your own, I would say read through how an open source OCR like Tesseract was implemented. Otherwise just google for OCR and you will find a list of OCR engines, both comercial and open-source. To list but a few: Tesseract: https://github.com/tesseract-ocr/...


2

It depends on the algorithm. A classical algorithm would not be able to recognize the pattern of primes unless it was programmed to do so. This pre-programming would not have to be exclusive to primes, but the algorithm would have to "understand" the nature of primes including 1 (the number can only be divided by 1 and itself.) Because computers are ...


2

That is one of the good example for research. Personally, I prefer to segment out all the desired outputs at once. Then, check the success rate. If you cannot hit the success rate that you desire, you can go for more specific solutions for the specific problem that you face. However, in general, the localization, segmentation, recognition are implemented in ...


2

Terms in a field are sometimes defined unambiguously. For instance, we know what convergence means when communicating about machine learning algorithms in academic publications because it has a formal definition in an older field, mathematics. However, the term machine learning is defined ambiguously across academic publications. Perspectives on Machine ...


2

You should look into unsupervised learning, which is machine learning without a training set. CNN's are cool but they need a training set.


2

You can search for the following paper titles: A Deep Multi-Level Network for Saliency Prediction. Beyond Universal Saliency: Personalized Saliency Prediction with Multi-task CNN. You can code in python using Pytorch framework.


2

First, the title mentions "sparse data". Recently the expression has taken a clear meaning: The agent input is data with mostly zeros. In the question a different meaning: A "sparse data stream", where data flows and vanishes sometimes. I understand the question as: "Will training an AI still work if the training data stream breaks?" Note the explicit "...


2

Digital Media Forensics (DMF) field aims to develop technologies for the automated assessment of the integrity of an image or video, so DMF is the field you are looking for. There are several approaches in DMF: for example, those based on machine learning (ML) techniques, in particular, convolutional neural networks (CNNs). For example, in the paper ...


2

Can AI provide a more reliable analysis of the gross effects of carbon emissions on extinctions of species ice-cap melting, and other effects? Yes. The work of Judea Pearl and others over the last 20 years began out of a desire to address uncertainty within AI. Eventually, this led Pearl to become fascinated by the need to quantifiably determine when one ...


2

Approaches There are two main approaches to detecting any human readable representation of a discrete quantity within text. Detect well known and stable patterns in the input stream and by adjacency determine the output stream. Windowing through the text in the input stream and directly detect the quantities. There are other approaches and there are ...


2

A understanding for this level of abstraction is technically possible. It is not hard to create an AI able to count. Unfortunately, this does not imply that the AI knows what 1 is. It knows: This is 1 piece of cake and this is 1 sheet of paper. But the idea of the number is not grasped yet. Also, animals can count, but they do not understand why it works. ...


2

Without knowing the kind of data and the process generating it it's hard to give a definite answer. In general, I would attempt a network that has as inputs the actual sensor readings, and outputs the expected readings. You train this network by presenting data with errors added as inputs, and correct readings as outputs. It should learn to guess the ...


2

Instead of using a neural network, simply sample as many non-anomalous readings from each sensor as you can. If the distribution of the readings from each sensor is approximately normal (check the skew and kurtosis values for the samples from each sensor) then you can work out mean and standard deviation of the samples and, for any future samples, the value ...


2

I would recommend a hierarchical cluster algorithm, after normalising your numbers into proportions. Then the clustering should be able to identify similar patterns. Depending at which level you make the cut, you can decide how many clusters you want. A great resource on this topic is Kaufman, L., & Roussew, P. J. (1990). "Finding Groups in Data - An ...


2

If I understand correctly you want to find companies with similar patterns to yours. I would start with measuring cosine similarity between your company and others. It is really easy with Python, for example: In [21]: from sklearn.metrics.pairwise import cosine_similarity In [22]: cosine_similarity([[1,4,2,6], [1,9,5,4]]) Out[22]: array([[1. , 0....


1

The Hough Transform extended to orthogonal ellipses uses this model, accumulating on $\theta$ for all $\{x, y\}$ with parameter matrix \begin{Bmatrix} c_x & c_y \\ r_x & r_y \end{Bmatrix} where $$1 = \dfrac {(x - c_x) \, \cos \theta} {r_x} + \dfrac {(y - c_y) \, \sin \theta} {r_y}$$ The question is looking to detect the normal lines, so any of ...


1

If want to use deep learning approaches, you should look to recurrent neural networks (RNN). Recurrent networks will take into account temporal dependencies and could detect thatn this in this Friday belong to datetime but not in this apple. As a simple model, you could create a model with a bidirectional LSTM layer (a type of RNN): Input: the sequences ...


1

I’m curious if this book is still relevant considering it was published in 2006? I signed up for loyal publication society that is accompanied by the secret society of scientists,it proposed the open global library. I haven't read through the book when I checked it out from the source but according to the reviews and citations globally,it has almost 4000 ...


1

I think context is important here. Using tactics like those used by Scotland Yard for over a century is probably the best way. Establishing alibis, realistic time lines, motives. For a legal setting, it would be possible to prove these images were fake using methods like this. From an I.T. perspective, it may be possible to pinpoint an origin for these ...


1

Would I be right in saying that this becomes a sort of 'pattern recognition' problem? Technically, yes. In practice: no. I think you might be interpreting the term "pattern recognition" a bit too literal. Even though wikipedia defines Pattern recognition as "a branch of machine learning that focuses on the recognition of patterns and regularities in data",...


1

It is an interesting application. It is possible. You can interpret sound as histogram (2D image) and apply same image processing techniques (CNN) to extract information. Alternatively, you can keep them as phase / intensity values and train a network on top of them (RNN). That is a great idea. Go for it!


1

In data mining, we can use machine learning (ML) (with the help of unsupervised learning algorithms) to recognize patterns. Pattern recognition is a process of recognizing patterns such as images or speech. We can recognise patterns using ML. For example, once a neural net is trained, using ML algorithms, it can be used for pattern recognition. Other ...


Only top voted, non community-wiki answers of a minimum length are eligible