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 ...


5

The most natural place where artificial networks can be used in information security is in attack detection. The security team leaders of more than one web hosting company told me the same story. Their teams' daily challenges are to defend against the attacks mounted continuously by several overseas teams against the IT security of their hosting ...


4

At first, you can find lots of information as pedestrian detection. As you are trying to localize game characters, the face is not the best option. You need to look for the character in general. About HAAR Cascades, the algorithm is one of the fastest face localization solutions in the market. The reason is, it applies all the feature classifications layer ...


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

Yes, in fact neural networks (NNs) are very efficient at segmentation and it seems to me that your problem matches the capabilities of neural networks very well. I think it best for you to truly understand what a NN is before using it. First, let's start with the architecture. A NN has 3 regions, the input layer, the hidden layers and the output layer. The ...


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

The terms you are looking for are deeplearning and convolutional neural networks for object detection. Google responds well to these terms. From academical point of view you can start from: Single shot multibox detector: https://arxiv.org/pdf/1512.02325v5.pdf Or Faster-RCNN: https://arxiv.org/pdf/1506.01497.pdf These are not simple architectures and there ...


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

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

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

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

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

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

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

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

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

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

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....


2

A simple initial approach would be to separate it by position and check for each: Use linear regression: $\hat{salary} = \sum_i \alpha_i * \hat{region}_i + \sum_k \beta_k * \mathbf{1}[\hat{gender}=k]$ and now you have an intuitive measure by looking at $\alpha$'s and $\beta$'s. 2 issues that may arise with this method: This assumes though that a linear ...


2

There are some unsupervised learning algorithms that can be used for pattern recognition (i.e. the discovery of patterns in data). The most notable one is probably k-means, which is a clustering algorithm. In k-means, you cluster your unlabeled data into groups (or clusters) based on the distance (or similarity) between them. When a new data point arrives, ...


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 ...


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