Cognitive computer

From HandWiki
Short description: Machine designed to physically mimic the human brain and host artificial intelligence

A cognitive computer is a computer that hardwires artificial intelligence and machine learning algorithms into an integrated circuit that closely reproduces the behavior of the human brain.[1] It generally adopts a neuromorphic engineering approach. Synonyms include neuromorphic chip and cognitive chip.[2][3]

In 2023, IBM's proof-of-concept NorthPole chip achieved state-of-the-art performance at image recognition.[4]

In 2013, IBM developed Watson, a cognitive computer implemented using neural networks and deep learning techniques.[5] The next year it developed the 2014 TrueNorth microchip architecture,[6] which is designed to be closer in structure to the human brain than the von Neumann architecture used in conventional computers.[1] In 2017 Intel also announced its version of a cognitive chip in "Loihi", which it intended to be available to university and research labs in 2018. Intel (most notably with its Pohoiki Beach and Springs systems[7][8]), Qualcomm, and others are improving neuromorphic processors steadily.

IBM TrueNorth chip

DARPA SyNAPSE board with 16 TrueNorth chips

TrueNorth was a neuromorphic CMOS integrated circuit produced by IBM in 2014.[9] It is a manycore processor network on a chip design, with 4096 cores, each one having 256 programmable simulated neurons for a total of just over a million neurons. In turn, each neuron has 256 programmable "synapses" that convey the signals between them. Hence, the total number of programmable synapses is just over 268 million (228). Its basic transistor count is 5.4 billion.

Details

Memory, computation, and communication are handled in each of the 4096 neurosynaptic cores, TrueNorth circumvents the von Neumann-architecture bottleneck and is very energy-efficient, with IBM claiming a power consumption of 70 milliwatts and a power density that is 1/10,000th of conventional microprocessors.[10] The SyNAPSE chip operates at lower temperatures and power because it only draws power necessary for computation.[11] Skyrmions have been proposed as models of the synapse on a chip.[12][13]

The neurons are emulated using a Linear-Leak Integrate-and-Fire (LLIF) model, a simplification of the leaky integrate-and-fire model.[14]

According to IBM, it doesn't have a clock,[15] operates on unary numbers and computes by counting to a maximum of 19 bits.[6][16] The said cores are event-driven by using both (a)synchronous logic and are interconnected through an asynchronous packet-switched mesh network on chip (NOC).[16]

IBM developed a new network to program and use TrueNorth. It included a simulator, a new programming language, an integrated programming environment, and even libraries.[15] This lack of backward compatibility with any previous technology (e.g., C++ compilers) poses serious vendor lock-in risks and other adverse consequences that may prevent it from commercialization in the future.[15][failed verification]

Research

In 2018 a cluster of TrueNorth network-linked to a master computer was used in stereo vision research that attempted to extract the depth of rapidly moving objects in a scene.[17]

IBM NorthPole chip

In 2023, IBM released its NorthPole chip, which is a proof-of-concept for dramatically improving performance by intertwining compute with memory on-chip, thus eliminating the Von Neumann bottleneck. It blends approaches from IBM's 2014 TrueNorth system with modern hardware designs to achieve speeds about 4,000 times faster than TrueNorth. It can run ResNet-50 or Yolo-v4 image recognition tasks about 22 times faster, with 25 times less energy and 5 times less space, when compared to GPUs which use the same 12-nm node process that it was fabricated with. It includes 224 MB of RAM and 256 processor cores and can perform 2,048 operations per core per cycle at 8-bit precision, and 8,192 operations at 2-bit precision. It runs at between 25 and 425 MHz. [4][18][19][20] This is an inferencing chip but it cannot handle GPT-4, yet.

Intel Loihi chip

Intel's self-learning neuromorphic chip, named Loihi (produced in 2017, perhaps named after the Hawaiian seamount Lōʻihi), offers substantial power efficiency. Intel claims Loihi is about 1000 times more energy efficient than the general-purpose computing power needed to train the neural networks that rival Loihi's performance. In theory, this would support both machine learning training and inference on the same silicon independently of a cloud connection, and more efficient than using convolutional neural networks (CNNs) or deep learning neural networks. Intel points to a system for monitoring a person's heartbeat, taking readings after events such as exercise or eating, and using the cognitive computing chip to normalize the data and work out the ‘normal’ heartbeat. It can then spot abnormalities, but also deal with any new events or conditions.

The first iteration of the Loihi chip was made using Intel's 14 nm fabrication process and houses 128 clusters of 1,024 artificial neurons each for a total of 131,072 simulated neurons.[21] This offers around 130 million synapses, which is still a rather long way from the human brain's 800 trillion synapses, and behind IBM's TrueNorth, which has around 256 million by using 64 by 4,096 cores.[22] Loihi is now available for research purposes among more than 40 academic research groups as a USB form factor.[23][24] Recent developments include a 64-core chip named Pohoiki Beach (after Isaac Hale Beach Park, also known as Pohoiki).[25]

In October 2019, researchers from Rutgers University published a research paper to demonstrate the energy efficiency of Intel's Loihi in solving Simultaneous localization and mapping.[26]

In March 2020, Intel and Cornell University published a research paper to demonstrate the ability of Intel's Loihi to recognize different hazardous materials, which could eventually aid to "diagnose diseases, detect weapons and explosives, find narcotics, and spot signs of smoke and carbon monoxide".[27]

Intel's Loihi 2, released in September 2021, boasts faster speeds, higher-bandwidth inter-chip communications for enhanced scalability, increased capacity per chip, a more compact size due to process scaling, and significantly improved programmability.[28]

SpiNNaker

SpiNNaker (Spiking Neural Network Architecture) is a massively parallel, manycore supercomputer architecture designed by the Advanced Processor Technologies Research Group at the Department of Computer Science, University of Manchester.[29]

Criticism

Critics argue that a room-sized computer – as in the case of IBM's Watson – is not a viable alternative to a three-pound human brain.[30] Some also cite the difficulty for a single system to bring so many elements together, such as the disparate sources of information as well as computing resources.[31]

In 2021, The New York Times released Steve Lohr's article "What Ever Happened to IBM’s Watson?".[32] He wrote about some costly failures of IBM Watson. One of them, the cancer-related project, named the Oncology Expert Advisor,[33] was abandoned in 2016 as a costly failure. During the collaboration, Watson could not use patient data. Watson struggled to decipher doctors’ notes and patient histories.

See also

References

  1. ↑ 1.0 1.1 Witchalls, Clint (November 2014). "A computer that thinks". New Scientist 224 (2994): 28–29. doi:10.1016/S0262-4079(14)62145-X. Bibcode: 2014NewSc.224...28W. 
  2. ↑ Seo, Jae-sun; Brezzo, Bernard; Liu, Yong; Parker, Benjamin D.; Esser, Steven K.; Montoye, Robert K.; Rajendran, Bipin; Tierno, José A. et al. (September 2011). "A 45nm CMOS neuromorphic chip with a scalable architecture for learning in networks of spiking neurons". 2011 IEEE Custom Integrated Circuits Conference (CICC). pp. 1–4. doi:10.1109/CICC.2011.6055293. ISBN 978-1-4577-0222-8. https://ieeexplore.ieee.org/document/6055293. Retrieved 21 December 2021. 
  3. ↑ "Samsung plugs IBM's brain-imitating chip into an advanced sensor". Engadget. https://www.engadget.com/2016-08-14-samsung-ibm-truenorth-chip-advanced-sensor.html?guccounter=1&guce_referrer=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8&guce_referrer_sig=AQAAAEyBOixzFCImIutPFUgAkRxxTA1zeRbUY1znwb6Tav5HJTSmOTyJYOunS7gf2kt6pJEjc2c9x-dH4dvwR6XVDfVgsge9otODfaasHx3cl2t09zBEWoY_kofdnZj8268FxsWac6u4qa1lnpWcxN3kLsI3djeubMT17Mtt8y3c2Uu8. 
  4. ↑ 4.0 4.1 "IBM Debuts Brain-Inspired Chip For Speedy, Efficient AI - IEEE Spectrum" (in en). https://spectrum.ieee.org/neuromorphic-computing-ibm-northpole. 
  5. ↑ KELLY, JOHN E.; HAMM, STEVE (2013). Smart Machines: IBM's Watson and the Era of Cognitive Computing. Columbia University Press. doi:10.7312/kell16856. ISBN 9780231537278. https://www.jstor.org/stable/10.7312/kell16856. 
  6. ↑ 6.0 6.1 "The brain's architecture, efficiency… on a chip" (in en-US). 2016-12-19. https://www.ibm.com/blogs/research/2016/12/the-brains-architecture-efficiency-on-a-chip/. 
  7. ↑ "Intel's Pohoiki Beach, a 64-Chip Neuromorphic System, Delivers Breakthrough Results in Research Tests". https://newsroom.intel.com/news/intels-pohoiki-beach-64-chip-neuromorphic-system-delivers-breakthrough-results-research-tests/. 
  8. ↑ "Korean Researchers Devel". 30 March 2020. http://www.businesskorea.co.kr/news/articleView.html?idxno=43451. 
  9. ↑ Merolla, P. A.; Arthur, J. V.; Alvarez-Icaza, R.; Cassidy, A. S.; Sawada, J.; Akopyan, F.; Jackson, B. L.; Imam, N. et al. (2014). "A million spiking-neuron integrated circuit with a scalable communication network and interface". Science 345 (6197): 668–73. doi:10.1126/science.1254642. PMID 25104385. Bibcode: 2014Sci...345..668M. 
  10. ↑ https://spectrum.ieee.org/computing/hardware/how-ibm-got-brainlike-efficiency-from-the-truenorth-chip How IBM Got Brainlike Efficiency From the TrueNorth Chip
  11. ↑ "Cognitive computing: Neurosynaptic chips". IBM. 11 December 2015. http://research.ibm.com/cognitive-computing/neurosynaptic-chips.shtml. 
  12. ↑ Song, Kyung Mee; Jeong, Jae-Seung; Pan, Biao; Zhang, Xichao; Xia, Jing; Cha, Sunkyung; Park, Tae-Eon; Kim, Kwangsu et al. (March 2020). "Skyrmion-based artificial synapses for neuromorphic computing". Nature Electronics 3 (3): 148–155. doi:10.1038/s41928-020-0385-0. 
  13. ↑ "Neuromorphic computing: The long path from roots to real life". 15 December 2020. https://venturebeat.com/2020/12/15/neuromorphic-computing-the-long-path-from-roots-to-real-life/. 
  14. ↑ "The brain's architecture, efficiency… on a chip" (in en-US). 2016-12-19. https://www.ibm.com/blogs/research/2016/12/the-brains-architecture-efficiency-on-a-chip/. 
  15. ↑ 15.0 15.1 15.2 "IBM Research: Brain-inspired Chip" (in en-ZZ). 9 February 2021. http://www.research.ibm.com/articles/brain-chip.shtml. 
  16. ↑ 16.0 16.1 Andreou, Andreas G.; Dykman, Andrew A.; Fischl, Kate D.; Garreau, Guillaume; Mendat, Daniel R.; Orchard, Garrick; Cassidy, Andrew S.; Merolla, Paul et al. (May 2016). "Real-time sensory information processing using the TrueNorth Neurosynaptic System". 2016 IEEE International Symposium on Circuits and Systems (ISCAS). pp. 2911. doi:10.1109/ISCAS.2016.7539214. ISBN 978-1-4799-5341-7. https://ieeexplore.ieee.org/document/7539214. 
  17. ↑ "Stereo Vision Using Computing Architecture Inspired by the Brain" (in en-US). 2018-06-19. https://www.ibm.com/blogs/research/2018/06/stereo-vision/. 
  18. ↑ Afifi-Sabet, Keumars (2023-10-28). "Inspired by the human brain — how IBM's latest AI chip could be 25 times more efficient than GPUs by being more integrated — but neither Nvidia nor AMD have to worry just yet" (in en). https://www.techradar.com/pro/inspired-by-the-human-brain-how-ibms-latest-ai-chip-could-be-25-times-more-efficient-than-gpus-by-being-more-integrated-but-neither-nvidia-nor-amd-have-to-worry-just-yet. 
  19. ↑ Modha, Dharmendra S.; Akopyan, Filipp; Andreopoulos, Alexander; Appuswamy, Rathinakumar; Arthur, John V.; Cassidy, Andrew S.; Datta, Pallab; DeBole, Michael V. et al. (2023-10-20). "Neural inference at the frontier of energy, space, and time" (in en). Science 382 (6668): 329–335. doi:10.1126/science.adh1174. ISSN 0036-8075. PMID 37856600. Bibcode: 2023Sci...382..329M. https://www.science.org/doi/10.1126/science.adh1174. 
  20. ↑ Modha, Dharmendra (2023-10-19). "NorthPole: Neural Inference at the Frontier of Energy, Space, and Time" (in en-US). https://modha.org/2023/10/northpole-neural-inference-at-the-frontier-of-energy-space-and-time/. 
  21. ↑ "Why Intel built a neuromorphic chip". https://www.zdnet.com/article/why-intel-built-a-neuromorphic-chip/. 
  22. ↑ ""Intel unveils Loihi neuromorphic chip, chases IBM in artificial brains". October 17, 2017. AITrends.com". https://aitrends.com/future-of-ai/intel-unveils-loihi-neuromorphic/. 
  23. ↑ Feldman, M. (7 December 2018). "Intel Ramps Up Neuromorphic Computing Effort with New Research Partners". TOP500. https://www.top500.org/news/intel-ramps-up-neuromorphic-computing-effort-with-new-research-partners. 
  24. ↑ Davies, M. (2018). "Loihi - a brief introduction". Intel Corporation. http://niceworkshop.org/wp-content/uploads/2018/05/Mike-Davies-NICE-Loihi-Intro-Talk-2018.pdf. 
  25. ↑ Hruska, J. (16 July 2019). "Intel's Neuromorphic Loihi Processor Scales to 8M Neurons, 64 Cores". Ziff Davis. https://www.extremetech.com/science/295043-intels-neuromorphic-loihi-processor-scales-to-8m-neurons-64-cores. 
  26. ↑ Tang, Guangzhi; Shah, Arpit; Michmizos, Konstantinos. (2019). "Spiking Neural Network on Neuromorphic Hardware for Energy-Efficient Unidimensional SLAM". 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). pp. 4176–4181. doi:10.1109/IROS40897.2019.8967864. ISBN 978-1-7281-4004-9. 
  27. ↑ Imam, Nabil; Cleland, Thomas A. (2020). "Rapid online learning and robust recall in a neuromorphic olfactory circuit". Nature Machine Intelligence 2 (3): 181–191. doi:10.1038/s42256-020-0159-4. 
  28. ↑ Peckham, Oliver (2022-09-28). "Intel Labs Launches Neuromorphic 'Kapoho Point' Board" (in en-US). https://www.hpcwire.com/2022/09/28/intel-labs-launches-neuromorphic-kapoho-point-board/. 
  29. ↑ "Research Groups: APT - Advanced Processor Technologies (School of Computer Science - the University of Manchester)". http://apt.cs.manchester.ac.uk/projects/SpiNNaker/project/. 
  30. ↑ Neumeier, Marty (2012). Metaskills: Five Talents for the Robotic Age. Indianapolis, IN: New Riders. ISBN 9780133359329. 
  31. ↑ Hurwitz, Judith; Kaufman, Marcia; Bowles, Adrian (2015). Cognitive Computing and Big Data Analytics. Indianapolis, IN: John Wiley & Sons. pp. 110. ISBN 9781118896624. 
  32. ↑ Lohr, Steve (2021-07-16). "What Ever Happened to IBM's Watson?" (in en-US). The New York Times. ISSN 0362-4331. https://www.nytimes.com/2021/07/16/technology/what-happened-ibm-watson.html. 
  33. ↑ Simon, George; DiNardo, Courtney D.; Takahashi, Koichi; Cascone, Tina; Powers, Cynthia; Stevens, Rick; Allen, Joshua; Antonoff, Mara B. et al. (June 2019). "Applying Artificial Intelligence to Address the Knowledge Gaps in Cancer Care". The Oncologist 24 (6): 772–782. doi:10.1634/theoncologist.2018-0257. ISSN 1083-7159. PMID 30446581. 

Further reading



Retrieved from "https://handwiki.org/wiki/index.php?title=Cognitive_computer&oldid=3431762"