Goto

Collaborating Authors

Interpretable Image Recognition with Hierarchical Prototypes

arXiv.org Machine Learning

Vision models are interpretable when they classify objects on the basis of features that a person can directly understand. Recently, methods relying on visual feature prototypes have been developed for this purpose. However, in contrast to how humans categorize objects, these approaches have not yet made use of any taxonomical organization of class labels. With such an approach, for instance, we may see why a chimpanzee is classified as a chimpanzee, but not why it was considered to be a primate or even an animal. In this work we introduce a model that uses hierarchically organized prototypes to classify objects at every level in a predefined taxonomy. Hence, we may find distinct explanations for the prediction an image receives at each level of the taxonomy. The hierarchical prototypes enable the model to perform another important task: interpretably classifying images from previously unseen classes at the level of the taxonomy to which they correctly relate, e.g. classifying a hand gun as a weapon, when the only weapons in the training data are rifles. With a subset of ImageNet, we test our model against its counterpart black-box model on two tasks: 1) classification of data from familiar classes, and 2) classification of data from previously unseen classes at the appropriate level in the taxonomy. We find that our model performs approximately as well as its counterpart black-box model while allowing for each classification to be interpreted.


Manitest: Are classifiers really invariant?

arXiv.org Machine Learning

Invariance to geometric transformations is a highly desirable property of automatic classifiers in many image recognition tasks. Nevertheless, it is unclear to which extent state-of-the-art classifiers are invariant to basic transformations such as rotations and translations. This is mainly due to the lack of general methods that properly measure such an invariance. In this paper, we propose a rigorous and systematic approach for quantifying the invariance to geometric transformations of any classifier. Our key idea is to cast the problem of assessing a classifier's invariance as the computation of geodesics along the manifold of transformed images. We propose the Manitest method, built on the efficient Fast Marching algorithm to compute the invariance of classifiers. Our new method quantifies in particular the importance of data augmentation for learning invariance from data, and the increased invariance of convolutional neural networks with depth. We foresee that the proposed generic tool for measuring invariance to a large class of geometric transformations and arbitrary classifiers will have many applications for evaluating and comparing classifiers based on their invariance, and help improving the invariance of existing classifiers.


Examples of Artificial Perceptions in Optical Character Recognition and Iris Recognition

arXiv.org Artificial Intelligence

This paper assumes the hypothesis that human learning is perception based, and consequently, the learning process and perceptions should not be represented and investigated independently or modeled in different simulation spaces. In order to keep the analogy between the artificial and human learning, the former is assumed here as being based on the artificial perception. Hence, instead of choosing to apply or develop a Computational Theory of (human) Perceptions, we choose to mirror the human perceptions in a numeric (computational) space as artificial perceptions and to analyze the interdependence between artificial learning and artificial perception in the same numeric space, using one of the simplest tools of Artificial Intelligence and Soft Computing, namely the perceptrons. As practical applications, we choose to work around two examples: Optical Character Recognition and Iris Recognition. In both cases a simple Turing test shows that artificial perceptions of the difference between two characters and between two irides are fuzzy, whereas the corresponding human perceptions are, in fact, crisp.


Amazon launches new artificial intelligence services for developers: Image recognition, text-to-speech, Alexa NLP

#artificialintelligence

Amazon today announced three new artificial intelligence-related toolkits for developers building apps on Amazon Web Services. At the company's AWS re:invent conference in Las Vegas, Amazon showed how developers can use three new services -- Amazon Lex, Amazon Polly, Amazon Rekognition -- to build artificial intelligence features into apps for platforms like Slack, Facebook Messenger, ZenDesk, and others. The idea is to let developers utilize the machine learning algorithms and technology that Amazon has already created for its own processes and services like Alexa. Instead of developing their own AI software, AWS customers can simply use an API call or the AWS Management Console to incorporate AI features into their own apps. AWS CEO Andy Jassy noted that Amazon has been building AI and machine learning technology for 20 years and said that there are now thousands of people "dedicated to AI in our business."


Amazon launches new artificial intelligence services for developers: Image recognition, text-to-speech, Alexa NLP

#artificialintelligence

Amazon today announced three new artificial intelligence-related toolkits for developers building apps on Amazon Web Services. At the company's AWS re:invent conference in Las Vegas, Amazon showed how developers can use three new services -- Amazon Lex, Amazon Polly, Amazon Rekognition -- to build artificial intelligence features into apps for platforms like Slack, Facebook Messenger, ZenDesk, and others. The idea is to let developers utilize the machine learning algorithms and technology that Amazon has already created for its own processes and services like Alexa. Instead of developing their own AI software, AWS customers can simply use an API call or the AWS Management Console to incorporate AI features into their own apps. AWS CEO Andy Jassy noted that Amazon has been building AI and machine learning technology for 20 years and said that there are now thousands of people "dedicated to AI in our business."