Request Expert

Expert provides custom analog IC design, mixed-signal and RF design, IC layout and verification, and development services. He also creates mixed-signal and analog modules for SoC and ASIC chips used in applications such as analog-front-ends (AFE) and transceiver modules for wireless, imaging, sensor interface, and communications. Expert’s experience and design methodology helps customers simultaneously optimize for low-power dissipation, low-voltage operation, very low-noise, low-distortion and high speed, required for battery powered applications and low cost system development. He has extensive design experience with low-power, high-speed, low-voltage analog-to-digital converters designed in deep sub micron process technologies such as 0.18um for mainstream digital CMOS technologies. Expert can assist ASIC developers with all stages of ASIC development, provide advice in early phases of ASIC definition such as concept feasibility, selecting compatible process technology selection, as well as system sub-block specification and partitioning. Expert can work with a chip integration team, sharing decades of mixed-signal ASIC development experience, to reduce cross-talk and increase isolation of sensitive analog modules.

Expert has experience with sensors, VLSI circuits and sensors interfaces, sensor networks, imager sensor networks, image sensors, biomedical circuits and systems. He also has experience in SOI, SOS design, silicon on insulator, and silicon on sapphire process, as well as analog and mixed-signal design of VLSI systems and circuits.

Expert provides custom analog IC design, mixed-signal and RF design, IC layout and verification, and development services for board design and system design. He also creates mixed-signal and analog modules for SoC and ASIC chips that are used in applications such as analog-front-ends (AFE) and transceiver modules for wireless, imaging, sensor interface, and communications. He has experience in chip design, board design and system design for sensors, sensor networks, and interfaces.

Expert has experience in the design and development of retinal implants and artificial vision sensors, image sensors, bio inspired sensors, biomimetic image sensors, and neuromorphic engineering sensors.

Expert has experience in biosensors design for patch clamp applications, neural recordings, neural stimulators, and telemetry.

Expert takes hints from nature and from other scientific research fields to add and improve on the performance, efficiency, and dynamic range of sensory circuits and systems. He targets biomedical application and uses modern fabrication technologies and thoughtful targeted design to engineer systems to improve everyday life and to help the scientific endeavor of understanding life at the pillars of creation.

We are developing synthetic models of the mammalian visual system in hardware. We design both bio-inspired image sensors
and hardware visual processing circuits.
This work was featured in the media (MSNBC, New York Times podcast, the Economist, International Business Times, Science
Daily, gizmag, Yale News, to name a few - Google "Neuflow" or "NeoVision + Expert" to get them all) in the Fall 2010.

We are developing bio-inspired neuromorphic algorithms and neural processing hardware to model the ventral pathways of the
mammalian visual system.
What does it take for a microchip to be able to:
- Find and categorize objects of interest in a scene?
- How do you find and define points of interest in a scene? Which attention algorithms?
- Is segmentation, stereo, optical flow and object categorization related? How?
- How can we track an object in the scene when its features change with each frame?
- How do we infer high-order behavior from a movie? What did that person just do in this movie?
Our goal is to provide an artificial vision system that is capable of performing at the same levels of the human visual system. In
order to do this, we embed all the top computer vision algorithms and vision neuroscience findings into a complex computer
designed to replicate human vision.
For this purpose, we are developing NeuFlow: a dataflow computer for bio-inspired visual processing aimed at speeding up the
computations of state-of-the-art vision algorithms and holistic vision systems. NeuFlow is a custom microprocessor with arrays
of computing elements suited to accelerate computations on videos and streaming data (data flow).
NeuFlow was first implemented for convolutional neural networks. These networks have been successfully used in many
recognition and classification tasks including document recognition, object recognition, face detection and robot navigation, and
combined with our Dataflow Computer, they can perform in real-time on megapixel-size video streams. Applications are in robotic
vision, security, monitoring and also in posture recognition, assisted living and remote care of elderly patients.