1. IEEE Signal Processing Magazine
2. Signal Processing Digital Library*
3. Inside Signal Processing Newsletter
4. SPS Resource Center
5. Career advancement & recognition
6. Discounts on conferences and publications
7. Professional networking
8. Communities for students, young professionals, and women
9. Volunteer opportunities
10. Coming soon! PDH/CEU credits
Click here to learn more.
10 years of news and resources for members of the IEEE Signal Processing Society
For our March 2015 issue, we cover recent patents granted in the area of Deep Lerning techniques. The section below covers patents granted recently for natural language processing, research of neural networks, correlation analysis between data streams, document analysis and medical image enhancement.
Specification of Patent no. 8,949,170 covers new algorithms, methods, and systems for artificial intelligence, soft computing, and deep learning/recognition, e.g., image recognition (e.g., for action, gesture, emotion, expression, biometrics, fingerprint, facial, OCR (text), background, relationship, position, pattern, and object), large number of images ("Big Data") analytics, machine learning, training schemes, crowd-sourcing (using experts or humans), feature space, clustering, classification, similarity measures, optimization, search engine, ranking, question-answering system, soft (fuzzy or unsharp) boundaries/impreciseness/ambiguities/fuzziness in language, Natural Language Processing (NLP), Computing-with-Words (CWW), parsing, machine translation, sound and speech recognition, video search and analysis (e.g. tracking), image annotation, geometrical abstraction, image correction, semantic web, context analysis, data reliability (e.g., using Z-number (e.g., "About 45 minutes; Very sure")), rules engine, control system, autonomous vehicle, self-diagnosis and self-repair robots, system diagnosis, medical diagnosis, biomedicine, data mining, event prediction, financial forecasting, economics, risk assessment, e-mail management, database management, indexing and join operation, memory management, and data compression.
In Patent no. 8,918,352 learning processes for a single hidden layer neural network, including linear input units, nonlinear hidden units, and linear output units, calculate the lower-layer network parameter gradients by taking into consideration a solution for the upper-layer network parameters. The upper-layer network parameters are calculated by a closed form formula given the lower-layer network parameters. An accelerated gradient algorithm can be used to update the lower-layer network parameters. A weighted gradient also can be used. With the combination of these techniques, accelerated training with faster convergence, to a point with a lower error rate, can be obtained.
The disclosed techniques of Patent no. 8,909,569 can provide users with a tool having an integrated, user-friendly interface and having automated mechanisms which can reveal correlations between data streams to the users in a clear and easily understandable way, thereby enabling the users to easily digest the vast amount of information contained in activities within one or more network, to understand the correlations among the activities, to stay informed and responsive to current or new trends, and even to predict future trends. Among other benefits, the disclosed techniques are especially useful in the context of discovering impacts of social networking activities on other types of commercial activities.
Methods and systems for document classification in Patent no. 8,892,488 include embedding n-grams from an input text in a latent space, embedding the input text in the latent space based on the embedded n-grams and weighting said n-grams according to spatial evidence of the respective n-grams in the input text, classifying the document along one or more axes, and adjusting weights used to weight the n-grams based on the output of the classifying step.
Embodiments of Patent no. 8,885,901 disclose systems and methods that aid in screening, diagnosis and/or monitoring of medical conditions. The systems and methods may allow, for example, for automated identification and localization of lesions and other anatomical structures from medical data obtained from medical imaging devices, computation of image-based biomarkers including quantification of dynamics of lesions, and/or integration with telemedicine services, programs, or software.
If you have an interesting patent to share when we next feature patents related to Deep Learning techniques, or if you are especially interested in a signal processing research field that you would want to be highlighted in this section, please send email to Csaba Benedek (benedek.csaba AT sztaki DOT mta DOT hu).
Title: System and method for analyzing ambiguities in language for natural language processing
Inventors: L. A. Zadeh
Issued: February 3, 2015
Assignee: Z Advanced Computing, Inc. (Potomac, MD)
Title: Learning processes for single hidden layer neural networks with linear output units
Inventors: L. Deng and D. Yu
Issued: December 23, 2014
Assignee: Microsoft Corporation (Redmond, WA))
Title: System and method for revealing correlations between data streams
Inventors: N. Spivack; D. ter Heide; Dominiek, S. A. Mousavi
Issued: December 9, 2014
Assignee: Bottlenose, Inc. (Sherman Oaks, CA)
Title: Document classification with weighted supervised n-gram embedding
Inventors: Y. Qi and B. Bai
Issued: November 18, 2014
Assignee: NEC Laboratories America, Inc. (Princeton, NJ))
Title: Systems and methods for automated enhancement of retinal images
Inventors: K. M. Solanki, Amai Ramachandra and B. Chaithanya
Issued: November 11, 2014
Assignee: Eyenuk, Inc. (Woodland Hills, CA))
© Copyright 2020 IEEE – All rights reserved. Use of this website signifies your agreement to the IEEE Terms and Conditions.
A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.