Showing posts with label Artificial neural networks. Show all posts
Showing posts with label Artificial neural networks. Show all posts




Project SyNAPSE (Systemsof Neuromorphic Adaptive Plastic Scalable Electronics) is a collaborativecognitive computing effort sponsored by the Defense Advanced Research ProjectsAgency to develop the architecture for a brain-inspired neurosynaptic computercore.

The project, which began in 2008, is a collaboration between IBM Research, HRL Laboratories, and Hewlett-Packard.

Researchers from a number of universities are also involved in the project.

The acronym SyNAPSE comes from the Ancient Greek word v, which means "conjunction," and refers to the neural connections that let information go to the brain.

The project's purpose is to reverse-engineer the functional intelligence of rats, cats, or potentially humans to produce a flexible, ultra-low-power system for use in robots.

The initial DARPA announcement called for a machine that could "scale to biological levels" and break through the "algorithmic-computational paradigm" (DARPA 2008, 4).

In other words, they needed an electronic computer that could analyze real-world complexity, respond to external inputs, and do so in near-real time.

SyNAPSE is a reaction to the need for computer systems that can adapt to changing circumstances and understand the environment while being energy efficient.

Scientists at SyNAPSE are working on neuromorphicelectronics systems that are analogous to biological nervous systems and capable of processing data from complex settings.

It is envisaged that such systems would gain a considerable deal of autonomy in the future.

The SyNAPSE project takes an interdisciplinary approach, drawing on concepts from areas as diverse as computational neuroscience, artificial neural networks, materials science, and cognitive science.

Basic science and engineering will need to be expanded in the following areas by SyNAPSE: 

  •  simulation—for the digital replication of systems in order to verify functioning prior to the installation of material neuromorphological systems.

In 2008, IBM Research and HRL Laboratories received the first SyNAPSE grant.

Various aspects of the grant requirements were subcontracted to a variety of vendors and contractors by IBM and HRL.

The project was split into four parts, each of which began following a nine-month feasibility assessment.

The first simulator, C2, was released in 2009 and operated on a BlueGene/P supercomputer, simulating cortical simulations with 109 neurons and 1013 synapses, similar to those seen in a mammalian cat brain.

Following a revelation by the Blue Brain Project leader that the simulation did not meet the complexity claimed, the software was panned.

Each neurosynaptic core is 2 millimeters by 3 millimeters in size and is made up of materials derived from human brain biology.

The cores and actual brains have a more symbolic than comparable relationship.

Communication replaces real neurons, memory replaces synapses, and axons and dendrites are replaced by communication.

This enables the team to explain a biological system's hardware implementation.

HRL Labs stated in 2012 that it has created the world's first working memristor array layered atop a traditional CMOS circuit.

The term "memristor," which combines the words "memory" and "transistor," was invented in the 1970s.

Memory and logic functions are integrated in a memristor.

In 2012, project organizers reported the successful large-scale simulation of 530 billion neurons and 100 trillion synapses on the Blue Gene/Q Sequoia machine at Lawrence Livermore National Laboratory in California, which is the world's second fastest supercomputer.

The TrueNorth processor, a 5.4-billion-transistor chip with 4096 neurosynaptic cores coupled through an intrachip network that includes 1 million programmable spiking neurons and 256 million adjustable synapses, was presented by IBM in 2014.

Finally, in 2016, an end-to-end ecosystem (including scalable systems, software, and apps) that could fully use the TrueNorth CPU was unveiled.

At the time, there were reports on the deployment of applications such as interactive handwritten character recognition and data-parallel text extraction and recognition.

TrueNorth's cognitive computing chips have now been put to the test in simulations like a virtual-reality robot driving and playing the popular videogame Pong.

DARPA has been interested in the construction of brain-inspired computer systems since the 1980s.

Dharmendra Modha, director of IBM Almaden's Cognitive ComputingInitiative, and Narayan Srinivasa, head of HRL's Center for Neural and Emergent Systems, are leading the Project SyNAPSE project.

~ Jai Krishna Ponnappan

Find Jai on Twitter | LinkedIn | Instagram

You may also want to read more about Artificial Intelligence here.

See also: 

Cognitive Computing; Computational Neuroscience.

References And Further Reading

Defense Advanced Research Projects Agency (DARPA). 2008. “Systems of Neuromorphic Adaptive Plastic Scalable Electronics.” DARPA-BAA 08-28. Arlington, VA: DARPA, Defense Sciences Office.

Hsu, Jeremy. 2014. “IBM’s New Brain.” IEEE Spectrum 51, no. 10 (October): 17–19.

Merolla, Paul A., et al. 2014. “A Million Spiking-Neuron Integrated Circuit with a Scalable Communication Network and Interface.” Science 345, no. 6197 (August): 668–73.

Monroe, Don. 2014. “Neuromorphic Computing Gets Ready for the (Really) Big Time.” Communications of the ACM 57, no. 6 (June): 13–15.

Artificial Intelligence in Medicine.


Artificial intelligence aids health-care providers by aiding with activities that need large-scale data management.

Artificial intelligence (AI) is revolutionizing how clinicians diagnose, treat, and predict outcomes in clinical settings.

In the 1970s, Scottish surgeon Alexander Gunn used computer analysis to assist diagnose nose severe abdominal discomfort, which was one of the earliest effective applications of artificial intelligence in medicine.

Artificial intelligence applications have risen in quantity and complexity since then, in line with advances in computer science.

Artificial neural networks, fuzzy expert systems, evolutionary computation, and hybrid intelligent systems are the most prevalent AI applications in medicine.

Artificial neural networks (ANNs) are brain-inspired systems that mimic how people learn and absorb information.

Warren McCulloch and Walter Pitts created the first artificial "neurons" in the mid-twentieth century.

Paul Werbos has just given artificial neural networks the capacity to execute backpropagation, which is the process of adjusting neural layers in response to new events.

ANNs are built up of linked processors known as "neurons" that process data in parallel.

In most cases, these neurons are divided into three layers: input, middle (or hidden), and output.

Each layer is completely related to the one before it.

Individual neurons are connected or linked, and a weight is assigned to them.

The technology "learns" by adjusting these weights.

The creation of sophisticated tools capable of processing nonlinear data and generalizing from inaccurate data sets is made feasible by ANNs.

Because of their capacity to spot patterns and interpret nonlinear data, ANNs have found widespread use in therapeutic contexts.

ANNs are utilized in radiology for image analysis, high-risk patient identification, and intensive care data analysis.

In instances where a variety of factors must be evaluated, ANNs are extremely beneficial for diagnosing and forecasting outcomes.

Artificial intelligence techniques known as fuzzy expert systems may operate in confusing situations.

In contrast to systems based on traditional logic, fuzzy systems are founded on the understanding that data processing often has to deal with ambiguity and vagueness.

Because medical information is typically complicated and imprecise, fuzzy expert systems are useful in health care.

Fuzzy systems can recognize, understand, manipulate, and use ambiguous information for a variety of purposes.

Fuzzy logic algorithms are being utilized to predict a variety of outcomes for patients with cancers including lung cancer and melanoma.

They've also been utilized to create medicines for those who are dangerously unwell.

Algorithms inspired by natural evolutionary processes are used in evolutionary computing.

Through trial and error, evolutionary computing solves issues by optimizing their performance.

They produce an initial set of solutions and then make modest random adjustments to the data set and discard failed intermediate solutions with each subsequent generation.

These solutions have been exposed to mutation and natural selection in some way.

As the fitness of the solutions improves, the consequence is algorithms that develop over time.

While there are many other types of these algorithms, the genetic algorithm is the most common one utilized in the field of medicine.

These were created in the 1970s by John Holland and make use of fundamental evolutionary patterns to build solutions in complicated situations like healthcare settings.

They're employed for a variety of clinical jobs including diagnostics, medical imaging, scheduling, and signal processing, among others.

Hybrid intelligent systems are AI technologies that mix many systems to take use of the advantages of the methodologies discussed above.

Hybrid systems are better at imitating human logic and adapting to changing circumstances.

These systems, like the individual AI technologies listed above, are being applied in a variety of healthcare situations.

Currently, they are utilized to detect breast cancer, measure myocardial viability, and interpret digital mammograms.

~ Jai Krishna Ponnappan

Find Jai on Twitter | LinkedIn | Instagram

You may also want to read more about Artificial Intelligence here.

See also: 

Clinical Decision Support Systems; Computer-Assisted Diagnosis; MYCIN; Precision Medicine Initiative.

References & Further Reading:

Baeck, Thomas, David B. Fogel, and Zbigniew Michalewicz, eds. 1997. Handbook of Evolutionary Computation. Boca Raton, FL: CRC Press.

Eiben, Agoston, and Jim Smith. 2003. Introduction to Evolutionary Computing. Berlin: Springer-Verlag.

Patel, Jigneshkumar L., and Ramesh K. Goyal. 2007. “Applications of Artificial Neural Networks in Medical Science.” Current Clinical Pharmacology 2, no. 3: 217–26.

Ramesh, Anavai N., Chandrasekhar Kambhampati, John R. T. Monson, and Patrick J. Drew. 2004. “Artificial Intelligence in Medicine.” Annals of the Royal College of Surgeons of England 86, no. 5: 334–38.

What Is Artificial General Intelligence?

Artificial General Intelligence (AGI) is defined as the software representation of generalized human cognitive capacities that enables the ...