Machine perception

Last updated

Machine perception is the capability of a computer system to interpret data in a manner that is similar to the way humans use their senses to relate to the world around them. [1] [2] [3] The basic method that the computers take in and respond to their environment is through the attached hardware. Until recently input was limited to a keyboard, or a mouse, but advances in technology, both in hardware and software, have allowed computers to take in sensory input in a way similar to humans. [1] [2]

Contents

Machine perception allows the computer to use this sensory input, as well as conventional computational means of gathering information, to gather information with greater accuracy and to present it in a way that is more comfortable for the user. [1] These include computer vision, machine hearing, machine touch, and machine smelling, as artificial scents are, at a chemical compound, molecular, atomic level, indiscernible and identical. [4] [5]

The end goal of machine perception is to give machines the ability to see, feel and perceive the world as humans do and therefore for them to be able to explain in a human way why they are making their decisions, to warn us when it is failing and more importantly, the reason why it is failing. [6] This purpose is very similar to the proposed purposes for artificial intelligence generally, except that machine perception would only grant machines limited sentience, rather than bestow upon machines full consciousness, self-awareness, and intentionality.

Machine vision

Computer vision is a field that includes methods for acquiring, processing, analyzing, and understanding images and high-dimensional data from the real world to produce numerical or symbolic information, e.g., in the forms of decisions. Computer vision has many applications already in use today such as facial recognition, geographical modeling, and even aesthetic judgment. [7]

However, machines still struggle to interpret visual impute accurately if said impute is blurry, and if the viewpoint at which stimulus are viewed varies often. Computers also struggle to determine the proper nature of some stimulus if overlapped by or seamlessly touching another stimulus. This refers to The Principle of Good Continuation. Machines also struggle to perceive and record stimulus functioning according to the Apparent Movement principle which Gestalt psychologists researched.

Machine hearing

Machine hearing, also known as machine listening or computer audition, is the ability of a computer or machine to take in and process sound data such as speech or music. [8] [9] This area has a wide range of application including music recording and compression, speech synthesis, and speech recognition. [10] Moreover, this technology allows the machine to replicate the human brain's ability to selectively focus on a specific sound against many other competing sounds and background noise. This particular ability is called "auditory scene analysis". The technology enables the machine to segment several streams occurring at the same time. [8] [11] [12] Many commonly used devices such as a smartphones, voice translators, and cars make use of some form of machine hearing. Present technology still occasionally struggles with speech segmentation though. This means hearing words within sentences, especially when human accents are accounted for.

Machine touch

A tactile sensor SynTouch BioTac.jpg
A tactile sensor

Machine touch is an area of machine perception where tactile information is processed by a machine or computer. Applications include tactile perception of surface properties and dexterity whereby tactile information can enable intelligent reflexes and interaction with the environment. [13] (This could possibly be done through measuring when and where friction occurs, and of what nature and intensity the friction is). Machines however still do not have any way of measuring some physical human experiences we consider ordinary, including physical pain. For example, scientists have yet to invent a mechanical substitute for the Nociceptors in the body and brain that are responsible for noticing and measuring physical human discomfort and suffering.

Machine olfaction

Scientists are developing computers known as machine olfaction which can recognize and measure smells as well. Airborne chemicals are sensed and classified with a device sometimes known as an electronic nose. [14] [15]

Machine taste

The electronic tongue is an instrument that measures and compares tastes. As per the IUPAC technical report, an “electronic tongue” as analytical instrument including an array of non-selective chemical sensors with partial specificity to different solution components and an appropriate pattern recognition instrument, capable to recognize quantitative and qualitative compositions of simple and complex solutions [16] [17]

Chemical compounds responsible for taste are detected by human taste receptors. Similarly, the multi-electrode sensors of electronic instruments detect the same dissolved organic and inorganic compounds. Like human receptors, each sensor has a spectrum of reactions different from the other. The information given by each sensor is complementary, and the combination of all sensors' results generates a unique fingerprint. Most of the detection thresholds of sensors are similar to or better than human receptors.

In the biological mechanism, taste signals are transduced by nerves in the brain into electric signals. E-tongue sensors process is similar: they generate electric signals as voltammetric and potentiometric variations.

Taste quality perception and recognition are based on the building or recognition of activated sensory nerve patterns by the brain and the taste fingerprint of the product. This step is achieved by the e-tongue's statistical software, which interprets the sensor data into taste patterns.

Future

Other than those listed above, some of the future hurdles that the science of machine perception still has to overcome include, but are not limited to:

- Embodied cognition - The theory that cognition is a full body experience, and therefore can only exist, and therefore be measure and analyzed, in fullness if all required human abilities and processes are working together through a mutually aware and supportive systems network.

- The Moravec's paradox (see the link)

- The Principle of similarity - The ability young children develop to determine what family a newly introduced stimulus falls under even when the said stimulus is different from the members with which the child usually associates said family with. (An example could be a child figuring that a chihuahua is a dog and house pet rather than vermin.)

- The Unconscious inference: The natural human behavior of determining if a new stimulus is dangerous or not, what it is, and then how to relate to it without ever requiring any new conscious effort.

- The innate human ability to follow the likelihood principle in order to learn from circumstances and others over time.

- The recognition-by-components theory - being able to mentally analyze and break even complicated mechanisms into manageable parts with which to interact with. For example: A person seeing both the cup and the handle parts that make up a mug full of hot cocoa, in order to use the handle to hold the mug so as to avoid being burned.

- The free energy principle - determining long before hand how much energy one can safely delegate to being aware of things outside one's self without the loss of the needed energy one requires for sustaining their life and function satisfactorily. This allows one to become both optimally aware of the world around them self without depleting their energy so much that they experience damaging stress, decision fatigue, and/or exhaustion.

See also

Related Research Articles

<span class="mw-page-title-main">Perception</span> Interpretation of sensory information

Perception is the organization, identification, and interpretation of sensory information in order to represent and understand the presented information or environment. All perception involves signals that go through the nervous system, which in turn result from physical or chemical stimulation of the sensory system. Vision involves light striking the retina of the eye; smell is mediated by odor molecules; and hearing involves pressure waves.

An illusion is a distortion of the senses, which can reveal how the mind normally organizes and interprets sensory stimulation. Although illusions distort the human perception of reality, they are generally shared by most people.

Bio-inspired computing, short for biologically inspired computing, is a field of study which seeks to solve computer science problems using models of biology. It relates to connectionism, social behavior, and emergence. Within computer science, bio-inspired computing relates to artificial intelligence and machine learning. Bio-inspired computing is a major subset of natural computation.

<span class="mw-page-title-main">Sensory nervous system</span> Part of the nervous system

The sensory nervous system is a part of the nervous system responsible for processing sensory information. A sensory system consists of sensory neurons, neural pathways, and parts of the brain involved in sensory perception and interoception. Commonly recognized sensory systems are those for vision, hearing, touch, taste, smell, balance and visceral sensation. Sense organs are transducers that convert data from the outer physical world to the realm of the mind where people interpret the information, creating their perception of the world around them.

Stimulus modality, also called sensory modality, is one aspect of a stimulus or what is perceived after a stimulus. For example, the temperature modality is registered after heat or cold stimulate a receptor. Some sensory modalities include: light, sound, temperature, taste, pressure, and smell. The type and location of the sensory receptor activated by the stimulus plays the primary role in coding the sensation. All sensory modalities work together to heighten stimuli sensation when necessary.

<span class="mw-page-title-main">Sensory neuron</span> Nerve cell that converts environmental stimuli into corresponding internal stimuli

Sensory neurons, also known as afferent neurons, are neurons in the nervous system, that convert a specific type of stimulus, via their receptors, into action potentials or graded receptor potentials. This process is called sensory transduction. The cell bodies of the sensory neurons are located in the dorsal ganglia of the spinal cord.

Voice leading is the linear progression of individual melodic lines and their interaction with one another to create harmonies, typically in accordance with the principles of common-practice harmony and counterpoint.

Sensory substitution is a change of the characteristics of one sensory modality into stimuli of another sensory modality.

In medicine and anatomy, the special senses are the senses that have specialized organs devoted to them:

<span class="mw-page-title-main">Electronic nose</span> Electronic sensor for odor detection

An electronic nose is an electronic sensing device intended to detect odors or flavors. The expression "electronic sensing" refers to the capability of reproducing human senses using sensor arrays and pattern recognition systems.

The electronic tongue is an instrument that measures and compares tastes. As per the IUPAC technical report, an “electronic tongue” as analytical instrument including an array of non-selective chemical sensors with partial specificity to different solution components and an appropriate pattern recognition instrument, capable to recognize quantitative and qualitative compositions of simple and complex solutions

Computer audition (CA) or machine listening is the general field of study of algorithms and systems for audio interpretation by machines. Since the notion of what it means for a machine to "hear" is very broad and somewhat vague, computer audition attempts to bring together several disciplines that originally dealt with specific problems or had a concrete application in mind. The engineer Paris Smaragdis, interviewed in Technology Review, talks about these systems — "software that uses sound to locate people moving through rooms, monitor machinery for impending breakdowns, or activate traffic cameras to record accidents."

Haptic perception means literally the ability "to grasp something". Perception in this case is achieved through the active exploration of surfaces and objects by a moving subject, as opposed to passive contact by a static subject during tactile perception.

<span class="mw-page-title-main">Odor</span> Volatile chemical compounds perceived by the sense of smell

An odor or odour is caused by one or more volatilized chemical compounds that are generally found in low concentrations that humans and many animals can perceive via their sense of smell. An odor is also called a "smell" or a "scent", which can refer to either an unpleasant or a pleasant odor.

Extinction is a neurological disorder that impairs the ability to perceive multiple stimuli of the same type simultaneously. Extinction is usually caused by damage resulting in lesions on one side of the brain. Those who are affected by extinction have a lack of awareness in the contralesional side of space and a loss of exploratory search and other actions normally directed toward that side.

A sense is a biological system used by an organism for sensation, the process of gathering information about the surroundings through the detection of stimuli. Although, in some cultures, five human senses were traditionally identified as such, many more are now recognized. Senses used by non-human organisms are even greater in variety and number. During sensation, sense organs collect various stimuli for transduction, meaning transformation into a form that can be understood by the brain. Sensation and perception are fundamental to nearly every aspect of an organism's cognition, behavior and thought.

<span class="mw-page-title-main">Tactile sensor</span>

A tactile sensor is a device that measures information arising from physical interaction with its environment. Tactile sensors are generally modeled after the biological sense of cutaneous touch which is capable of detecting stimuli resulting from mechanical stimulation, temperature, and pain. Tactile sensors are used in robotics, computer hardware and security systems. A common application of tactile sensors is in touchscreen devices on mobile phones and computing.

Many types of sense loss occur due to a dysfunctional sensation process, whether it be ineffective receptors, nerve damage, or cerebral impairment. Unlike agnosia, these impairments are due to damages prior to the perception process.

Robotic sensing is a subarea of robotics science intended to provide sensing capabilities to robots. Robotic sensing provides robots with the ability to sense their environments and is typically used as feedback to enable robots to adjust their behavior based on sensed input. Robot sensing includes the ability to see, touch, hear and move and associated algorithms to process and make use of environmental feedback and sensory data. Robot sensing is important in applications such as vehicular automation, robotic prosthetics, and for industrial, medical, entertainment and educational robots.

<span class="mw-page-title-main">Andranik Tangian</span> Soviet-German polymath (born 1952)

Andranik Semovich Tangian (Melik-Tangyan) ; born March 29, 1952) is a Soviet Armenian-German mathematician, political economist and music theorist. He is professor of the Institute for Economics (ECON) of the Karlsruhe Institute of Technology.

References

  1. 1 2 3 Malcolm Tatum (October 3, 2012). "What is Machine Perception".
  2. 1 2 Alexander Serov (January 29, 2013). "Subjective Reality and Strong Artificial Intelligence". arXiv: 1301.6359 [cs.AI].
  3. "Machine Perception & Cognitive Robotics Laboratory". www.ccs.fau.edu. Retrieved 2016-06-18.
  4. Cotton2009-03-01T00:00:00+00:00, Simon. "If it smells - it's chemistry". RSC Education. Retrieved 2022-05-03.{{cite web}}: CS1 maint: numeric names: authors list (link)
  5. "Artificial networks learn to smell like the brain". MIT News | Massachusetts Institute of Technology. Retrieved 2022-05-03.
  6. "Machine Perception Research - ECE - Virginia Tech". www.ECE.VT.edu. Archived from the original on March 7, 2021. Retrieved January 10, 2018.
  7. Dhar, Sagnik; Ordonez, Vicente; Berg, Tamara L. (2011). "High level describable attributes for predicting aesthetics and interestingness" (PDF). CVPR 2011. pp. 1657–1664. doi:10.1109/CVPR.2011.5995467. hdl:1951/55408. ISBN   978-1-4577-0394-2. S2CID   14609200.
  8. 1 2 Tanguiane (Tangian), Andranick (1993). Artificial Perception and Music Recognition. Berlin-Heidelberg: Springer.
  9. Tanguiane (Tangian), Andranick (1994). "Principle of correlativity of perception and its applications to music recognition". Music Perception. 11 (4): 465–502. doi:10.2307/40285634. JSTOR   40285634.
  10. Lyon, Richard (2010). "Machine Hearing: An Emerging Field [Exploratory DSP". IEEE Signal Processing Magazine. 27 (5): 131–139. Bibcode:2010ISPM...27..131L. doi:10.1109/MSP.2010.937498. S2CID   13143070.
  11. Tangian, Andranik (2001). "How do we think: modeling interactions of memory and thinking". Cognitive Processing. 2: 117–151. doi:10.5445/IR/1000133287. S2CID   237995668.
  12. "Machine Perception & Cognitive Robotics Laboratory". ccs.FAU.edu. Retrieved January 10, 2018.
  13. Fleer, S.; Moringen, A.; Klatzky, R. L.; Ritter, H. (2020). "Learning efficient haptic shape exploration with a rigid tactile sensor array, S. Fleer, A. Moringen, R. Klatzky, H. Ritter". PLOS ONE. 15 (1): e0226880. doi: 10.1371/journal.pone.0226880 . PMC   6940144 . PMID   31896135.
  14. "Using artificial intelligence to smell the roses: Study applies machine learning to olfaction with possible vast applications in flavors and fragrances". ScienceDaily. Retrieved 2022-05-03.
  15. Marr, Bernard. "Artificial Intelligence Is Developing A Sense Of Smell: What Could A Digital Nose Mean In Practice?". Forbes. Retrieved 2022-05-03.
  16. Vlasov, Yu; Legin, A.; Rudnitskaya, A.; Natale, C. Di; D'Amico, A. (2005-01-01). "Nonspecific sensor arrays ("electronic tongue") for chemical analysis of liquids (IUPAC Technical Report)". Pure and Applied Chemistry. 77 (11): 1965–1983. doi: 10.1351/pac200577111965 . ISSN   0033-4545. S2CID   109659409.
  17. Khalilian, Alireza; Khan, Md. Rajibur Rahaman; Kang, Shin-Won (2017). "Highly sensitive and wide-dynamic-range side-polished fiber-optic taste sensor". Sensors and Actuators B: Chemical. 249: 700–707. doi:10.1016/j.snb.2017.04.088.
  18. Turk, Matthew (2000). "Perceptive Media: Machine Perception and Human Computer Interaction" (PDF). Chinese Journal of Computers. 12. pages 1235-1244