Ofer, Israel

Shlomo Raikin

This inventor holds 25 USPTO granted patents and 1 EPO patent, primarily in Deep Learning Architectures. Top assignees: Mellanox Technologies, Ltd., Habana Labs Ltd.. Active years: 2017-2025.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Shlomo Raikin. Retrieved from https://idiyas.com/inventor/shlomo-raikin-pb3em6qs

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank

% Patents Active = 100.0


Average Co-Inventor Count = 3.6

ph-index = 9

Forward Citations = 298(Granted Patents)


Location History:

  • Kibutz Yassur, IL (2017 - 2018)
  • Kibbutz Yassur, IL (2017 - 2020)
  • Yokneam, IL (2020)
  • Moshav Ofer, IL (2017 - 2022)
  • Yassur, IL (2019 - 2022)
  • Tel Aviv-Jaffa, IL (2022)

Company Filing History:


Years Active: 2017-2025

Loading Chart...
Loading Chart...
Areas of Expertise:
Machine Learning
Tensor-Based Memory
Deep Neural Networks
Memory Access
Network Traffic Management
Remote Direct Memory Access
Data Compression
Computational Accelerator
Multicore Systems
Peripheral Device Control
Network-Attached Memory
PCI-E Access
25 patents (USPTO):Explore Patents

Title: Shlomo Raikin: Innovator in Neural Networks and Memory Access Technologies

Introduction

Shlomo Raikin is an accomplished inventor based in Moshav Ofer, Israel, with a remarkable portfolio comprising 24 patents. He has significantly contributed to advancements in computational apparatuses that enhance deep learning models and memory access techniques.

Latest Patents

Raikin's recent patents showcase his innovative approach to solving complex technological challenges. One of his latest inventions is the “Activation function approximation in deep neural networks using rectified-linear-unit function.” This patent describes a computational apparatus designed to implement a neural network model comprising multiple neurons that evaluate an activation function. The apparatus integrates a memory system that stores values of a difference function, which indicates the variance between the activation function and a predefined baseline function. Moreover, the circuitry is meticulously designed to evaluate the neural network model by dynamically retrieving values from memory, ensuring efficient processing of activation functions.

Another significant patent is related to “Tensor-based memory access,” which presents a processor featuring an internal memory and processing circuitry. This innovation allows the internal memory to store definitions of multi-dimensional arrays designated in external memories, enabling effective access through multi-dimensional coordinates specified by the indices. The processing circuitry executes a defined Instruction Set Architecture (ISA), facilitating enhanced operations on the multi-dimensional arrays.

Career Highlights

Shlomo Raikin has made his mark at notable organizations, including Mellanox Technologies and Habana Labs. His experience at these companies has allowed him to collaborate on groundbreaking projects in the field of computing technologies, particularly focusing on neural networks and memory systems.

Collaborations

Throughout his career, Raikin has worked alongside esteemed colleagues such as Noam Bloch and Michael Kagan. These collaborations have fostered an environment of innovation and have contributed to the successful development of his patented technologies.

Conclusion

Shlomo Raikin stands out as a notable inventor in the field of technological innovations, particularly in neural network functionalities and memory architectures. With a compelling array of patents to his name, his contributions are poised to impact the future of computing and artificial intelligence significantly.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…