ANALOG COMPUTATION IS BACK

WHAT

Artificial Intelligence is here, not only to stay, but to change our world. A long time ago Humans invented the wheel to move faster and to help relieving their muscles by heavy jobs. Today we, Humans, are shaping and developing the AI, to help our most important muscle, the brain, to go further and open new unthinkable landscapes, new opportunities and new jobs. Mentium has the technology to bring ultra-fast AI to low power electronics, like cameras, sensors, microphones, wearable accessories, and bringing the performances of autonomous vehicles and AI cloud computing to a whole new level.

WHY

TECHNOLOGY

Our architecture is based on Non-Volatile Memory devices used to carry out analog in-memory computation, eliminating the memory transfer bottleneck and exploiting the inherent efficiency of analog computation. Analog computing is an old concept abandoned a long time ago due to its troubles dealing with variations and noise, leading to low precision computation. Mentium Technologies Inc. solved these issues and our technology showed incredible resilience to temperature and device variations: we are able to deliver extremely fast and efficient AI computation.

TEAM

Dr. Mirko Prezioso
Dr. Mirko Prezioso
CEO
Dr. Farnood Merrikh Bayat
Dr. Farnood Merrikh Bayat
CTO
Prof. Dimitri Strukov
Prof. Dimitri Strukov
Chair
Prof. Konstantin Likharev
Prof. Konstantin Likharev
Board Member
Prof. John Bowers
Prof. John Bowers
Board Member
John LeMoncheck
John LeMoncheck
Advisory Board Member
Dr. Mirko Prezioso

Dr. Mirko Prezioso

CEO

Dr. Prezioso received his M.S. and Ph.D. degrees from Parma University, Italy. He worked at National Research Council in Bologna on the spintronic-memristive effects in organic materials and then moved to the University of California in Santa Barbara where he joined the Prof. Strukov’s group to pursue his interests in memristive systems.
With a theoretical condensed matter physics background, a long experience in experimental device physics, device fabrication and their simulation.
Lead scientist for the first demonstration of neuromorphic hardware based on integrated memristors. 

Dr. Farnood Merrikh Bayat

Dr. Farnood Merrikh Bayat

CTO

Farnood Merrikh Bayat received his M.Sc. and first Ph.D. in Electrical Engineering from Sharif University of Technology, Iran. He then joined the Computer Engineering Department of University of California Santa Barbara to earn his second Ph.D. where he later served as a PostDoc for two years. Dr. Merrikh Bayat has worked in the fields of signal processing, fuzzy logic, approximate computing, analog circuit design, nanoelectronics and neuro-fuzzy computing systems but his current research interests are in the design and hardware implementation of high-performance deep neural networks and neuromorphic systems based on nanoelectronics memory devices such as memristor and floating-gate (flash) transistor. Notably, he was the lead scientist for the first successful demonstration of large-scale neural network hardware based on integrated floating-gate transistors.

Prof. Dimitri Strukov

Prof. Dimitri Strukov

Chair

Dmitri B. Strukov received the M.S. degree in applied physics and mathematics from the Moscow Institute of Physics and Technology, Moscow, Russia in 1999, and the Ph.D. degree in electrical engineering from Stony Brook University, Stony Brook, NY, USA, in 2006. He is currently a Professor of Electrical and Computer Engineering at University of California at Santa Barbara. Prior to joining UC Santa Barbara, Dr. Strukov worked as a postdoctoral associate at Hewlett Packard Laboratories on various aspects of nanoelectronic computing systems. His research broadly concerns different aspects of computation, addressing computation efficiency on various levels of abstraction, and spans across different disciplines including material science, device physics, circuit design, high level computer architecture, and algorithms with the emphasis on the emerging device technologies. In the past several years, his major focus was on metal-oxide memristors and floating-gate circuits for neurocomputing. His group was the first to demonstrate pattern classification task with memristor crossbar circuits and redesigned NOR flash memory. Dr. Strukov has received 14 patents and published more than 100 original research publications, which have won best paper awards on multiple occasions.

Prof. Konstantin Likharev

Prof. Konstantin Likharev

Board Member

Konstantin K. Likharev received the Candidate (Ph.D.) degree in Physics from the Lomonosov Moscow State University, Russia in 1969, and the habilitation degree of Doctor of Sciences from the Higher Attestation Committee of the U.S.S.R. in 1979. From 1969 to 1988 Dr. Likharev was a Staff Scientist of Moscow State University, and from 1989 to 1991 the Head of the Laboratory for Cryoelectronics of that university. In 1991 he assumed a Professorship at Stony Brook University (Distinguished Professor since 2002). During his research career, Dr. Likharev worked in the fields of nonlinear classical and dissipative quantum dynamics, and solid-state physics and electronics, notably including superconductor electronics and nanoelectronics. His current research interests are in the architecture and nanoelectronic implementation of high-performance neuromorphic networks. Dr. Likharev is an author of more than 350 original publications, 80+ review papers and book chapters, 2 monographs, an online lecture note series “Essential Graduate Physics”, and several patents. He is a Fellow of the APS and IEEE.

Prof. John Bowers

Prof. John Bowers

Board Member

John E. Bowers holds the Fred Kavli Chair in Nanotechnology, and is the Director of the Institute for Energy Efficiency and a Professor in the Departments of Materials and Electrical and Computer Engineering at UCSB. He is a cofounder of Aurrion, Aerius Photonics and Calient Networks. Dr. Bowers received his M.S. and Ph.D. degrees from Stanford University and worked for AT&T Bell Laboratories and Honeywell before joining UC Santa Barbara. Dr. Bowers is a member of the National Academy of Engineering and the National Academy of Inventors. He is a fellow of the IEEE, OSA and the American Physical Society, and a recipient of the IEEE Photonics Award, OSA Tyndal Award, the OSA Holonyak Prize, the IEEE LEOS William Streifer Award and the South Coast Business and Technology Entrepreneur of the Year Award. He has published eight book chapters, 700 journal papers, 900 conference papers and has received 64 patents. He and coworkers received the EE Times Annual Creativity in Electronics (ACE) Award for Most Promising Technology for the hybrid silicon laser in 2007.

John LeMoncheck

John LeMoncheck

Advisory Board Member

A distinguished leader of both startups and public companies, LeMoncheck was most recently President & CEO at Cambrios, the leading provider of nanotechnology formulations for transparent electrodes for touch screens, photovoltaics, and OLED displays. Prior to Cambrios, LeMoncheck was president and CEO at SiBEAM, a pioneer in CMOS millimeter wave solutions and developer of high-speed wireless communications technology. Under LeMoncheck’s leadership, SiBEAM successfully shipped WirelessHD products to the consumer electronics and PC markets and was acquired by Silicon Image in 2011.

Before joining SiBEAM, LeMoncheck was VP of Consumer Electronics for Silicon Image, where he led the company's successful launch and commercialization of the HDMI standard. An industry veteran, LeMoncheck held executive roles at various technology companies including TeraLogic, subsequently purchased by Zoran and now owned by Qualcomm, Arithmos, Inc., which was successfully acquired by STMicroelectronics and was also a member of technical staff at Synaptics.

LeMoncheck has served on a number of industry leadership groups including the Global Semiconductor Alliance’s Startup CEO Council. He has a bachelor's of science degree in Electrical Engineering from U.C. San Diego and spent several years researching neuromorphic systems and VLSI for neural networks at Caltech and holds several patents.

CAREERS

Open Position as Deep Learning Scientist

At Mentium we are developing the next generation of Artificial Intelligence processors and.. we are hiring!
We are looking for a full-time Deep Learning Scientist, someone ready to accept the challenge of moving into uncharted territory and pushing the envelope of Neuromorphic Computing. You, as a Deep Learning Scientist, will interact with the electronic engineers to adapt current deep learning algorithms to our architecture as well as developing new innovative solutions. You are going to have the great opportunity to grow in an early stage company, working in a friendly environment on a disruptive technology for Artificial Intelligence.
So, what will you be doing?
  • Building and tuning neural networks
  • Participating in brainstorming and interacting with hardware engineers
  • Rapidly modifying standard Tensorflow libraries
  • Staying up to date with, and in some cases advancing the state of the art in machine learning applications
What do you need?
  • At lest 2 years in Deep Learning project developments
  • Excellent C/C++ programming skills
  • Excellent Python programming skills
  • Great passion for Artificial Intelligence and the knowledge of the latest architectures
  • Commitment and curiosity, a drive to work without supervision
  • Previous experience in customizing CUDA libraries is a plus!
If you feel this post describes you, and you are willing to live in the Santa Barbara area, California,
then send us your Resume at

jobs@mentium.tech




Open position as Digital CMOS Designer

Mentium Technologies is an early stage company working on the next generation of AI processors. We are searching for someone willing to work in uncharted territory and pushing the envelope of Artificial Intelligence Processors. The ideal candidate will be ready to be flexible in his role, interact with Analog designers, Deep Learning Scientists and Business developers to deliver the optimal solutions.
The primary responsibility for this position is digital architecture design with a particular emphasis on the memory, datapath and I/O flow.
What will you do?
  • Architecture and microarchitecture definition
  • Establishing design practices for first-pass success
What you should have:
  • BS/MS/PhD in EE/CS/CSE
  • Minimum 2 years of industry experience
  • RTL, memory management and design, microarchitecture, and architecture design experience of advanced microprocessors.
  • Experience designing digital computational components such as ALU, multipliers, FPU, etc…
  • Understanding of computing and memory architectures.
  • Understanding of timing constraints.
These are pluses
  • Experience working at startups
  • Experience with Python
  • Experience with C++
  • Experience with formal verification and IP integration
  • Experience working with embedded cores (ARM, etc..)
This position requires a full-time commitment and a VISA status to live and work in the Santa Barbara, California, area.

Send us your Resume at

jobs@mentium.tech

TOGGLE MAP

CONTACT



California NanoSystems Institute, University of California Santa Barbara, CA 93106-6105, USA

NAME
Email
SEND
Error: Please complete all fields and include a valid email
Thankyou, your enquiry has been sent!
©Copyright 2016-2018 Mentium Technologies Inc.