A5042044567- Photorefractive and Nonlinear Optics
- Photonic and Optical Devices
- Solid State Laser Technologies
- Advanced Fiber Laser Technologies
- Laser Design and Applications
- Semiconductor Lasers and Optical Devices
- Advanced Memory and Neural Computing
- CCD and CMOS Imaging Sensors
- Advanced Optical Sensing Technologies
- Optical and Acousto-Optic Technologies
- Advanced Fiber Optic Sensors
- Quantum Information and Cryptography
- Neural dynamics and brain function
- Ferroelectric and Piezoelectric Materials
- Ocular and Laser Science Research
- Nonlinear Optical Materials Research
- Acoustic Wave Resonator Technologies
- Laser-Matter Interactions and Applications
- Neuroscience and Neural Engineering
- Neural Networks and Applications
- Semiconductor Quantum Structures and Devices
- Spectroscopy and Laser Applications
- Mechanical and Optical Resonators
- Quantum optics and atomic interactions
- Phase-change materials and chalcogenides
IBM (United States)
1994-2023
IBM Research - Almaden
2002-2015
Bowling Green State University
2003
University of Warwick
1999
Stanford University
1984-1986
Inspired by the brain's structure, we have developed an efficient, scalable, and flexible non-von Neumann architecture that leverages contemporary silicon technology. To demonstrate, built a 5.4-billion-transistor chip with 4096 neurosynaptic cores interconnected via intrachip network integrates 1 million programmable spiking neurons 256 configurable synapses. Chips can be tiled in two dimensions interchip communication interface, seamlessly scaling to cortexlike sheet of arbitrary size. The...
The new era of cognitive computing brings forth the grand challenge developing systems capable processing massive amounts noisy multisensory data. This type intelligent poses a set constraints, including real-time operation, low-power consumption and scalability, which require radical departure from conventional system design. Brain-inspired architectures offer tremendous promise in this area. To end, we developed TrueNorth, 65 mW neurosynaptic processor that implements non-von Neumann,...
Many solid-state lasers of current interest exhibit reabsorption loss. Previous modeling calculations laser performance with longitudinal pumping either have neglected loss or been valid only for certain special cases the ratio pump- and laser-beam waists. Rigorous numerical carried out to provide a comprehensive understanding behavior longitudinally pumped lasers, including arbitrary sizes In addition, aspects that traditionally not discussed in papers on modeling, such as clamping,...
Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards TrueNorth cognitive computing system inspired by brain's function and efficiency. Judiciously balancing dual objectives functional capability implementation/operational cost, we develop simple, digital, reconfigurable, versatile spiking neuron model that supports one-to-one equivalence between hardware simulation is implementable using only 1272 ASIC gates. Starting with classic leaky integrate-and-fire...
IBM's brain-inspired processor is a massively parallel neural network inference engine containing 1 million spiking neurons and 256 low-precision synapses. Now, after decade of fundamental research spanning neuroscience, architecture, chips, systems, software, algorithms, IBM has delivered the largest neurosynaptic computer ever built.
Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards TrueNorth cognitive computing system inspired by brain's function and efficiency. The sequential programming paradigm von Neumann architecture is wholly unsuited for TrueNorth. Therefore, as our main contribution, we develop new that permits construction complex algorithms applications while being efficient effective programmer productivity. consists (a) an abstraction program, named Corelet, representing...
The grand challenge of neuromorphic computation is to develop a flexible brain-inspired architecture capable wide array real-time applications, while striving towards the ultra-low power consumption and compact size biological neural systems. Toward this end, we fabricated building block modular architecture, neurosynaptic core. Our implementation consists 256 integrate-and-fire neurons 1,024×256 SRAM crossbar memory for synapses that fits in 4.2mm <sup...
Marching along the DARPA SyNAPSE roadmap, IBM unveils a trilogy of innovations towards TrueNorth cognitive computing system inspired by brain's function and efficiency. The non-von Neumann nature architecture necessitates novel approach to efficient design. To this end, we have developed set abstractions, algorithms, applications that are natively for TrueNorth. First, repeatedly-used abstractions span neural codes (such as binary, rate, population, time-to-spike), long-range connectivity,...
Computing, since its inception, has been processor-centric, with memory separated from compute. Inspired by the organic brain and optimized for inorganic silicon, NorthPole is a neural inference architecture that blurs this boundary eliminating off-chip memory, intertwining compute on-chip, appearing externally as an active chip. low-precision, massively parallel, densely interconnected, energy-efficient, spatial computing co-optimized, high-utilization programming model. On ResNet50...
An ultra-thin phase-change bridge (PCB) memory cell, implemented with doped GeSb, is shown < 100muA RESET current. The device concept provides for simplified scaling to small cross-sectional area (60nm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> ) through (3nm) films; the GeSb material offers potential both fast crystallization and good data retention
We have developed a system for quantum key distribution (QKD), based on standard telecommunication lasers, detectors, and optical fiber, that passively compensates time-dependent variations of the fiber-optic path due to stress, temperature changes, or birefringence. This approach allows information encoded in phase shifts imposed single-photon-level pulses be accurately read out after transmission over many kilometers uncontrolled fiber. Cooled InGaAs avalanche photodiodes, pulse-biased...
We propose a physical model that quantitatively describes the behavior of dark count probability and single-photon quantum efficiency avalanche diodes under conditions allow these devices to be used for detection. The shows analytically how various parameters such as current, dc gain, Geiger mode carrier detrap time, pulse repetition rate, etc., can affect photodiode. theory agrees well with experimental results.
The authors have produced periodic poling in c-cut KTiOPO4 by applying an electric field to a sample having electrode on the –c face and uniform +c face. domain reversal occurred through 1 mm thickness of sample, was confirmed second-harmonic generation.
We report the use of GaAlAs laser-diode arrays to pump a cw Nd:YAG laser operating on 946-nm 4F3/2 → 4I9/2 transition. At room temperature, lasing threshold was reached with 58 mW absorbed power, and, 175 42 output power at 946 nm obtained in TEM00 mode by using 0.7% coupling. In addition, pumping an infrared dye pure used investigate effects reabsorption loss that are characteristic LiIO3 as intracavity doubling crystal, and 100 μW blue light generated diode-laser nonoptimized cavity.
Inspired by the function, power, and volume of organic brain, we are developing TrueNorth, a novel modular, non-von Neumann, ultra-low compact architecture. TrueNorth consists scalable network neurosynaptic cores, with each core containing neurons, dendrites, synapses, axons. To set sail for developed Compass, multi-threaded, massively parallel functional simulator compiler that maps long-distance pathways in macaque monkey brain to TrueNorth. We demonstrate near-perfect weak scaling on 16...
Inspired by the function, power, and volume of organic brain, we are developing TrueNorth, a novel modular, non-von Neumann, ultra-low compact architecture. TrueNorth consists scalable network neurosynaptic cores, with each core containing neurons, dendrites, synapses, axons. To set sail for developed Compass, multi-threaded, massively parallel functional simulator compiler that maps long-distance pathways in macaque monkey brain to TrueNorth. We demonstrate near-perfect weak scaling on 16...
Drawing on neuroscience, we have developed a parallel, event-driven kernel for neurosynaptic computation, that is efficient with respect to memory, and communication. Building the previously demonstrated highly optimized software expression of kernel, here, demonstrate True North, co-designed silicon kernel. North achieves five orders magnitude reduction in energy to-solution two speedup time-to solution, when running computer vision applications complex recurrent neural network simulations....
The wavelength, angle, and temperature tolerances of a new room-temperature noncritically phase-matched frequency mixing process involving type II 1064 809 nm radiation in potassium titanyl phosphate (KTiOPO4) are measured. angular bandwidths found to be unusually wide. Device applications for upconversion diode pumped neodymium:yttrium aluminum garnet laser sources the blue spectral region explored.
We have employed the “3ω method” to determine thermal conductivities of amorphous and crystalline phases technologically important materials Ge2Sb2Te5, nitrogen-doped Ag- In-doped Sb2Te, Ge15Sb85. used voltage” as a monitor conductivity that allowed us observe amorphous-to-crystalline phase transition material was annealed. For these materials, our results reveal κ is related electrical σ by an empirical relationship form κ=σLT+0.175 W/m K, where L Lorenz number T temperature.
This paper describes the hardware and software ecosystem encompassing brain-inspired TrueNorth processor - a 70mW reconfigurable silicon chip with 1 million neurons, 256 synapses, 4096 parallel distributed neural cores. For systems, we present scale-out system loosely coupling 16 single-chip boards scale-up tightly integrating chips in 4 × configuration by exploiting TrueNorth's native tiling. software, an end-to-end consisting of simulator, programming language, integrated environment,...
Quantum cryptographic key distribution (QKD) uses extremely faint light pulses to carry quantum information between two parties (Alice and Bob), allowing them generate a shared, secret key. Autocompensating QKD systems automatically passively compensate for uncontrolled time-dependent variations of the optical fibre properties by coding as differential phase orthogonally polarized components pulse sent on round trip through fibre, reflected at mid-course using Faraday mirror. We have built...
We have integrated a commercial avalanche photodiode (APD) and the circuitry needed to operate it as single-photon detector (SPD) onto single PC-board. At temperatures accessible with Peltier coolers (~200-240K), PCB-SPD achieves high detection efficiency (DE) at 1308 1545 nm low dark count probability (e.g. ~10-6/bias pulse DE=20%, 220 K), making useful for quantum key distribution (QKD). The board generates fast bias pulses, cancels noise transients, amplifies signals, sends them an...
Optical waveguides can be formed in potassium titanyl phosphate (KTiOPO4, KTP) crystals by an ion-exchange process. Waveguides were fabricated KTP substrates exchanging rubidium ions for ions. The resulting refractive index profile was measured as a function of diffusion time and temperature. Based on these characterization measurements, the phase-matching properties planar waveguide guided-wave second-harmonic generation modeled. Second-harmonic blue/green light observed at wavelengths...