This inventor holds 2 USPTO granted patents and 5 published patent applications. Top assignees: Google Inc., Yissum Research Development Company of the Hebrew University of Jerusalem Ltd.. Active years: 2017-2024.
Company Filing History:


Years Active: 2017-2024
Title: Yedid Hoshen: Innovator in Deep Learning and Audio Processing
Introduction
Yedid Hoshen is a prominent inventor based in Jerusalem, Israel. He has made significant contributions to the fields of deep learning and audio processing, holding a total of 2 patents. His innovative work focuses on enhancing the capabilities of technology through advanced methodologies.
Latest Patents
Yedid Hoshen's latest patents include a method for deep learning-based anomaly detection in images. This method involves receiving training images that predominantly represent normal data instances and a target image. It extracts feature representations from both the training images and the target image, calculates distances between these representations, and determines if the target image location is anomalous based on a predetermined threshold.
Another notable patent involves processing multi-channel audio waveforms. This method enhances speech recognition by utilizing various neural network processing techniques. It includes receiving multiple channels of audio data, convolving filters with the audio waveform data, and inputting the combined outputs into a deep neural network to provide accurate transcriptions of utterances.
Career Highlights
Throughout his career, Yedid Hoshen has worked with leading companies such as Google Inc. and Yissum Research Development Company of the Hebrew University of Jerusalem Ltd. His experience in these organizations has allowed him to refine his skills and contribute to groundbreaking projects in technology.
Collaborations
Yedid has collaborated with notable individuals in his field, including Tara N. Sainath and Ron J. Weiss. These collaborations have further enriched his work and expanded the impact of his innovations.
Conclusion
Yedid Hoshen stands out as an influential inventor whose work in deep learning and audio processing continues to shape the technological landscape. His patents reflect a commitment to advancing the capabilities of artificial intelligence and speech recognition.