{"id":77,"date":"2021-02-08T23:36:18","date_gmt":"2021-02-08T23:36:18","guid":{"rendered":"http:\/\/adaptivecomputation.com\/?page_id=77"},"modified":"2026-01-16T05:32:36","modified_gmt":"2026-01-16T05:32:36","slug":"technology","status":"publish","type":"page","link":"https:\/\/adaptivecomputation.com\/index.php\/technology\/","title":{"rendered":"Technology"},"content":{"rendered":"\r\n

ADC Background<\/strong><\/h2>\r\n\r\n\r\n\r\n

Work on EViP technology was initiated by ADC\u2019s founder, Dr. Tuan A Duong, while he was working at NASA\u2019s Jet Propulsion Laboratory, in one of three frontier neural network teams in the United States (including AT&T Bell Labs and Bellcore) in 1984.\u00a0\u00a0<\/p>\r\n\r\n\r\n\r\n

Some of the relevant projects Dr. Duong researched and developed during his time at JPL include:<\/p>\r\n\r\n\r\n\r\n\r\n\r\n

*\u00a0Real-Time Mars Landing Site Identification\u00a0 based on real-time color segmentation and adaptation, supported by Self-Evolving Neural Network Architecture namely Cascade Error Projection, to survey and identify a\u00a0safe<\/strong>\u00a0and\u00a0productive<\/strong> landing site in real-time;<\/em><\/p>\r\n\r\n\r\n\r\n

* Self-Evolving Neural Network Architecture Supervised Learning algorithm to identify Amino Acid building blocks for Life Detection Mission.<\/em><\/p>\r\n\r\n\r\n\r\n

* Space Invariant Independent Component Analysis (SPICA) for recovering the original odorant sources from unknown mixtures for ENose (a multi-element chemical sensor) in an open unknown environment (Caltech patent).<\/em><\/p>\r\n\r\n\r\n\r\n

* Introductory Extended Visual Pathway Data Flow, a technology which has now been fully developed at ADC (Caltech patent).<\/em><\/p>\r\n\r\n\r\n\r\n

* Cognitive Computing Architecture that enables a general-purpose neural processor chip to be equipped with a compiler, making low power, compactness, and real-time adaptive operation available in a single package.\u00a0 This set a cornerstone for intelligent perception and recognition in hardware implementation (Caltech patent).<\/em><\/p>\r\n\r\n\r\n\r\n

* Others.<\/em><\/p>\r\n\r\n\r\n\r\n

With his 12 patents with NASA or Caltech Assignee, 5 patents with ADC Assignee, and nine of them are neural networks related technology.<\/p>\r\n\r\n\r\n\r\n

These technologies have provided the foundation for the technologies ADC has now brought to fruition.\u00a0 NASA\/JPL-Caltech provided generous support and\u00a0an\u00a0excellent environment for doing this preliminary research.\u00a0 Involvement through licensing and other arrangements continues to be a key to ADC\u2019s success.<\/p>\r\n\r\n\r\n\r\n

Our Technology<\/strong><\/h2>\r\n\r\n\r\n\r\n

At Adaptive Computation LLC, Dr. Tuan A Duong invented the Extended Visual Pathway (EViP) approach as an unsupervised learning approach to integrate a saccadic eye movement emulator with a bio-inspired visual processing pathway to enable the detection and recognition of generic full\/partial\/low resolution\/ sketched\/degraded objects in open and ambiguous environments.\u00a0 This basic technology is protected by US and international patents.<\/p>\r\n

He also invented a new learning architecture to enable the machine to self-learn new objects autonomously and additively in a sequential manner when the objects arrive and appear at different times. Hence the cognitive and perceptive capability can be equipped for machine intelligence.\u00a0<\/p>\r\n\r\n\r\n\r\n\r\n\r\n

Extended Visual Pathway (EViP)<\/h4>\r\n\r\n\r\n\r\n

EViP consists of a saccadic eye movement emulator and visual pathway filters and visual cortex.<\/p>\r\n\r\n\r\n\r\n

\"\"<\/figure>\r\n

\u00a0<\/h3>\r\n

SOFTWARE\u00a0<\/strong><\/h3>\r\n

Unsupervised learning (EViP.1)<\/strong><\/h3>\r\n

Bio-inspired Extended Visual Pathway (EViP) software, which integrates a saccadic eye movement emulator with an advanced model of the human visual pathway, to enable real-time processing for the detection and recognition of single<\/strong> or multiple<\/strong> objects in real-time and on-line<\/strong>, given inputs that are:<\/p>\r\n

    \r\n
  • partial-view or full-view<\/li>\r\n
  • low resolution or \u201cnoisy\u201d<\/li>\r\n
  • incomplete or \u201ccollage\u201d style<\/li>\r\n
  • sketches of actual objects.<\/li>\r\n<\/ul>\r\n

    to search for similar objects in an uncontrolled environments.<\/p>\r\n

    EViP along with high floating-point computation (32 bit) has demonstrated with 10,000 distractors, EViP outperforms Human Visual Systems, providing 66% versus 24% correct recognition in rank 1.<\/p>\r\n

    With effective bio-inspired features, it enables real-time adaptive capability to meet the dynamic change, to serve as a short-term memory operations.<\/p>\r\n

    Face Detection and Recognition in Single Faces Database using OE Sensing Data<\/strong><\/p>\r\n