Baidu Backs Neuromorphic IC Developer

发布时间:2018-11-19 00:00
作者:Ameya360
来源:eetimes
阅读量:946

Swiss startup aiCTX has closed a $1.5 million pre-A funding round from Baidu Ventures to develop commercial applications for its low-power neuromorphic computing and processor designs and enable what it calls “neuromorphic intelligence.” It is targeting low-power edge-computing embedded sensory processing systems.

Founded in March 2017 based on advances in neuromorphic computing hardware developed at the Institute of Neuroinformatics of the University of Zurich and ETH Zurich, aiCTX (pronounced “AI-cortex”) is developing “full-stack” custom neuromorphic processors for a variety of artificial-intelligence (AI) edge-computing applications that require ultra-low-power and ultra-low-latency features, including autonomous robots, always-on co-processors for mobile and embedded devices, wearable health-care systems, security, IoT applications, and computing at the network edge.

Dylan Muir, senior R&D engineer at aiCTX, told EE Times that the company is building end-to-end dedicated neuromorphic IP blocks, ASICs, and SoCs as full custom computing solutions that integrate neuromorphic sensors and processors. “This approach ensures minimum size and power consumption and is fundamentally different from most other neuromorphic computing approaches that propose general-purpose solutions as a plug-and-play alternative to parts of machine-learning tool chains with conventional data paths.”

He added, “We engineer spiking neural network and algorithmic solutions that implement computational neuroscience models of cortical computation. Our technology is based on over 20 years of research and development in neuromorphic models of cortical computation that started out at CALTECH in the mid-’90s and are still ongoing at the Institute of Neuroinformatics of the University of Zurich and ETH Zurich.”

Baidu Ventures’ CEO, Wei Liu, said that they invested in aiCTX because it is different from other neuromorphic startups and corporations active in the field in that it has a unique technology and a product-driven focus. “They are developing complete commercial solutions, not simply designing computing fabrics,” he said.

We asked Muir what that meant. He said that, at the moment, other neuromorphic solutions target desktop applications and are based on a standard clocked digital logic design flow. In contrast, aiCTX designs are either based on ultra-low-power mixed-signal analog-digital VLSI circuits or on fully asynchronous low-power hand-crafted digital designs (or both). “We are targeting applications that require ultra-low power (sub-mW to mW) always-on solutions for IoT edge-based computing on mobile and embedded systems that do not need to rely on the cloud,” said Muir.

He added, “We are building demos around those applications and finding potential industrial partners. For example, we’re partnering with a health wearable company to provide ultra-low-power on-board signal processing using our neuromorphic processors.”

Muir said that the company is currently finalizing its new DynapCNN chip, which is a scalable, fully configurable digital event-driven neuromorphic processor with 1M ReLU spiking neurons per chip for implementing spiking convolutional neural networks (sCNN). The chip supports various types of CNN layers (like ReLU, Cropping, Padding, and Pooling) and network architectures (like LeNet, ResNet, and Inception). The technology is aimed at always-on, ultra-low-power and ultra-low-latency event-driven sensory processing applications. Samples of the chip will be available during Q2 of 2019.

In addition, aiCTX said that it is building a new family of neuromorphic chips that combine energy efficiency with features for low-latency, real-time end-to-end applications. The design will provide interfaces for converting analog sensory signals into spikes and for direct event-based input from dynamic-vision sensors, making the devices suitable for mobile health and robotics applications. This neuromorphic processor will tape-out by the end of 2018. The first development kits, along with a software development ecosystem, are planned to be released in Q3 of 2019.

A fully neuromorphic smart vision processor is also under development by a joint venture between aiCTX and neuromorphic vision systems company iniVation. This is a compact, low-cost, single-chip solution for ultra-low-power (sub-mW) and ultra-low-latency (<10 ms) always-on IoT devices and edge-computing vision applications, such as gesture recognition, face or object detection, and surveillance. Samples of smart vision processors are planned for Q4 of 2019.

In terms of business model, aiCTX is developing whole chip solutions for demonstrating and exploring potential applications but, in the long term, hopes to license and provide IP solutions. “The goal is to follow a model similar to that of Arm for the whole IoT edge-computing landscape,” commented Muir. “The IP provided by aiCTX will be tailored exactly to customer and application needs for maximum efficiency.”

Muir said that because the company is developing what it believes is a completely new and disruptive approach to computing, this requires developments at all levels of the hierarchy from the basic computing devices to their design and configuration tools, the high-level algorithmic development, and the testing framework. Now that the optimal solutions and market needs are being identified, aiCTX can expand its chip design and system engineering activities and is starting to talk to investors for a Series A round in the next month. “Baidu Ventures’ investment will help us grow our team, so we can move faster on the applications we’ve identified,” he said.

aiCTX Vision

The company told us that its vision is to develop this technology to solve AI problems and create a whole new field of research that will be called NI (for “neuromorphic intelligence”). Muir said that the landscape of computing is rapidly changing from bulky and power-hungry general-purpose computing systems to small, task-specific, low-power edge-computing embedded sensory processing systems.

The spiking sensory and neural processing systems studied at the Institute of Neuroinformatics of the University of Zurich and ETH Zurich demonstrate that brain-inspired architectures can implement low-power computations efficiently and robustly. “The vision of the company is to exploit the know-how accumulated over the years in studying beyond-von-Neumann computational paradigms and to develop engineering solutions that have high potential in the growing IoT market,” added Muir.

In particular, the last two years have seen tremendous leaps in state-of-the-art neural-network algorithms, especially in the context of application-oriented spiking neural networks. This has paved the path for demonstrable gains in the use of neuromorphic devices for solving complex pattern recognition and classification tasks.

Muir summarized, “Our approach is to deliver not only new hardware tailored for a given application but to provide a full working solution — that means that we also develop neural-network configurations for the neuromorphic devices in-house. We have a research team within aiCTX to build full applications around our neuromorphic hardware.”

(备注:文章来源于网络,信息仅供参考,不代表本网站观点,如有侵权请联系删除!)

在线留言询价

相关阅读
Nikon, ASML and Carl Zeiss sign agreement to settle all litigation
US cancels trade planning meeting with China, source says
  The White House rejected a trade planning meeting with Chinese counterparts this week due to outstanding disagreements between the two sides over the enforcement of intellectual property rules.  Officials from the U.S. trade representative's office were set to meet with two Chinese vice ministers this week to try to resolve trade differences before the March 1 deadline, but the meeting was called off, a source familiar with the situation confirmed to CNBC's Kayla Tausche.  Should Beijing and Washington fail to agree on a permanent solution, President Donald Trump has said he will reinforce punitive tariffs on roughly half of all Chinese exports to the U.S.  Asked for comment, the White House told CNBC that "the teams remain in touch in preparation for high level talks with Vice Premier Liu He at the end of this month." The Treasury Department and the U.S. trade representative's office did not respond to requests for comment.  White House economic advisor Larry Kudlow denied that an official meeting had been canceled, telling CNBC on Tuesday that no intermediate meetings had been scheduled other than the visit by Liu next week.  One source suggested that talks may still happen over the phone, but the termination of the in-person visit signals that reaching a complete agreement beyond the basic tenants of the Group of 20 truce will be difficult. China offered to boost its imports from the U.S. for six years, officials familiar with the matter told CNBC last week, though how any such promise would be enforced remains uncertain.  Chinese officials made the offer during negotiations in Beijing earlier in January, Bloomberg News reported. China would increase its annual import of U.S. goods by a combined value of more than $1 trillion, the officials told Bloomberg, which was the first to report on the import boost offer.  "I would kind of characterize negotiations as generally moving in the right direction. Last week, China offered a fig leaf in lowering tariff rates and agreed to import a trillion dollars of U.S. goods by 2024," said Joseph Lupton, global economist at J.P. Morgan.  Trade negotiations between Washington and Beijing have stretched for months amid a tit-for-tat dispute. Both countries have slapped tariffs on billions of dollars worth of each others' goods. The White House put tariffs of 10 percent on $200 billion of Chinese productsin September and at the time threatened to increase the levy to 25 percent by the start of 2019.  The two nations late last year agreed to halt additional tariffs as they engage in new trade talks with the goal of reaching an agreement before the March deadline following Trump's meeting with Chinese President Xi Jinping in Argentina.  "I think there's a lot of posturing going on. Trump's tweeting the China numbers are weak, they better make a deal quick," Lupton added. "I think a lot of that posturing is what's taking place here but beneath the surface both sides see a need to get some sort of deal here. It's just a matter of spinning it as a win for the two sides."
2019-01-23 00:00 阅读量:1635
Perforce Software to acquire Rogue Wave Software
  Perforce Software, a developer of enterprise-grade DevOps-focused software solutions, is to acquire Rogue Wave Software, an independent provider of cross-platform software developer tools and embedded components.  The new combination of Perforce and Rogue Wave is intended to deliver a full suite of solutions that will not only improve developer productivity but support DevOps at scale. This is the sixth acquisition by Perforce in the last two years since embarking on an aggressive growth strategy to expand its portfolio across the technology development lifecycle.  Terms of the deal are not being disclosed, although the acquisition is expected to close in February of this year.  Rogue Wave provides solutions that help enterprises to optimise their software development and build, connect, and secure applications. The company has relationships with more than 5,600 customers across industries including financial services, technology, healthcare, government, entertainment, and manufacturing. Based in Louisville, Colorado, the company has 16 offices throughout the world.  “This transformational acquisition further expands our global footprint and broadens our offerings. Rogue Wave’s software suite strengthens Perforce’s existing static code analysis and automated test offerings, and also adds new capabilities in the areas of dynamic code analysis, API management, project visualization, developer productivity, and embedded analytics,” said Mark Ties, Perforce CEO.  Perforce continues to build out its DevOps-focused software portfolio that looks to meet the needs of technology development teams that are challenged with multiple dimensions of scale but still must deliver products securely at a rapid pace.  "Software development is growing increasingly complex, driving the need for platforms and solutions that can help enterprises simplify their applications and shorten cycle times. With continuously evolving customer demands, it has never been more important for enterprises to deliver high-quality products and solutions quickly," said Brian Pierce, Rogue Wave CEO.
2019-01-23 00:00 阅读量:1817
Pushing the boundaries of semiconductors
  Scientists from the university of Freiburg, the Sustainability Center Freiburg and the Fraunhofer-Gesellschaft have joined forces in order to explore a new material structure that may be better suited for future power electronics.  The study, Power Electronics 2020, has led them to explore a piezoelectric semiconductor, a material with a high dielectric strength known as scandium aluminium nitride (ScAlN).  Silicon has dominated the electronics industry. With its relatively low cost and an almost perfect crystal structure, it has become a particularly successful semiconductor material. Moreover, its bandgap allows for both a good charge carrier concentration and velocity as well as a good dielectric strength. Despite its benefits, silicon electronics is gradually reaching its physical limit. Especially with regard to the increasing demand for power density and compactness.  The limitations of silicon technology have already been overcome by the use of gallium nitride (GaN) as a semiconductor in power electronics. GaN performs better in conditions of high voltages, high temperatures and fast switching frequencies compared to silicon. This also allows for higher energy efficiency, thereby reducing energy consumption.  Fraunhofer IAF has been researching GaN as a semiconductor material for electronic components and systems for many years. With the help of industrial partners, the results of this work have already been put to commercial use. The Power Electronics 2020 team is now looking towards the next step, enhancing the energy efficiency and durability of next generation electronic systems once more.  ScAlN is largely unexplored worldwide with regard of its usability in microelectronic applications. But its suitability for power electronic components has already been proven, says the team. The aim of the project is to grow lattice-matched ScAlN on a GaN layer and to use the resulting heterostructures to process transistors with high current carrying capacity.  Functional semiconductor structures based on materials with a large bandgap, such as ScAlN and GaN, allow for transistors with very high voltages and currents. These devices reach a higher power density per chip surface as well as higher switching speeds and higher operating temperatures. This is synonymous with lower switching losses, higher energy efficiency and more compact systems. By combining both materials, the researchers want to double the maximal possible output power of our devices while at the same time significantly lowering the energy demand.  One of the biggest challenges of the project is crystal growth because their existing structures neither growth recipes nor empirical values. The project team is looking to develop these during the next months in order to reach reproducible results and to produce layer structures that can successfully be used for power electronic applications.
2019-01-22 00:00 阅读量:1310
  • 一周热料
  • 紧缺物料秒杀
型号 品牌 询价
TL431ACLPR Texas Instruments
RB751G-40T2R ROHM Semiconductor
MC33074DR2G onsemi
BD71847AMWV-E2 ROHM Semiconductor
CDZVT2R20B ROHM Semiconductor
型号 品牌 抢购
BP3621 ROHM Semiconductor
ESR03EZPJ151 ROHM Semiconductor
BU33JA2MNVX-CTL ROHM Semiconductor
STM32F429IGT6 STMicroelectronics
IPZ40N04S5L4R8ATMA1 Infineon Technologies
TPS63050YFFR Texas Instruments
热门标签
ROHM
Aavid
Averlogic
开发板
SUSUMU
NXP
PCB
传感器
半导体
相关百科
关于我们
AMEYA360微信服务号 AMEYA360微信服务号
AMEYA360商城(www.ameya360.com)上线于2011年,现 有超过3500家优质供应商,收录600万种产品型号数据,100 多万种元器件库存可供选购,产品覆盖MCU+存储器+电源芯 片+IGBT+MOS管+运放+射频蓝牙+传感器+电阻电容电感+ 连接器等多个领域,平台主营业务涵盖电子元器件现货销售、 BOM配单及提供产品配套资料等,为广大客户提供一站式购 销服务。