Neuromorphic Computing Changes Machine Learning

Neuromorphic computing is a method of computer engineering in which elements of a computer are modeled after systems in the human brain and nervous system. The term refers to the design of both hardware and software computing elements. Neuromorphic computing is sometimes referred to as neuromorphic engineering. 

Unlike some of the future computing technologies, numerous physical realisations of neuromorphic hardware are now currently under development or are even available for use to the research community. A number of research institutions have been working for the past few years to find new concepts of how computers can better process data in the future. 

One of these concepts is “neuromorphic computing”, a method of computer engineering in which aspects of a computer are modeled like human brain and nervous systems. Compared to traditional Artificial Intelligence (AI) algorithms that have to be trained on large amounts of data before they can be effective, neuromorphic computing systems can learn and adapt as they go.

With the machine learning world growing so quickly, German researchers have devised an efficient training method for neuromorphic computers. Florian Marquardt, a scientist at the Max Planck Institute for the Science of Light in Erlangen, Germany, explains: “We have developed the concept of a self-learning physical machine. The core idea is to carry out the training in the form of a physical process, in which the parameters of the machine are optimised by the process itself.”

The model will require external feedback to improve, as in training conventional artificial neural networks, but the self-learning physical machine the researchers propose makes the training much more efficient and saves energy.

“Our method works regardless of which physical process takes place in the self-learning machine, and we do not even need to know the exact process,” explains Marquardt. “However, the process must fulfill a few conditions. Most importantly, it must be reversible, meaning it must be able to run forwards or backward with a minimum of energy loss.”

Computer hardware today is based  on Von Neumann architecture, which is the opposite of a neuromorphic architecture.  The researchers state in their study that the von Neumann architecture currently used in electronic devices is highly inefficient for most machine-learning applications. 

“We hope to be able to present the first self-learning physical machine in three years.... We are therefore confident that self-learning physical machines have a strong chance of being used in the further development of AI.” said Marquardt.

Arxiv:     Intel:    Nature:    I-HLS:    TechTarget:    Frontiers:  Cambridge Consultants:   Interesting Engineering:

Image: Planet Volumes

You Might Also Read: 

Musk's Brain Chip Firm Gets US Approval for Human Analysis:

___________________________________________________________________________________________

If you like this website and use the comprehensive 6,500-plus service supplier Directory, you can get unrestricted access, including the exclusive in-depth Directors Report series, by signing up for a Premium Subscription.

  • Individual £5 per month or £50 per year. Sign Up
  • Multi-User, Corporate & Library Accounts Available on Request

Cyber Security Intelligence: Captured Organised & Accessible


 

 

« Cyber War Crimes Will Be Prosecuted
The Battlefield Transformed »

Infosecurity Europe
CyberSecurity Jobsite
Perimeter 81

Directory of Suppliers

ZenGRC

ZenGRC

ZenGRC (formerly Reciprocity) is a leader in the GRC SaaS landscape, offering robust and intuitive products designed to make compliance straightforward and efficient.

CYRIN

CYRIN

CYRIN® Cyber Range. Real Tools, Real Attacks, Real Scenarios. See why leading educational institutions and companies in the U.S. have begun to adopt the CYRIN® system.

XYPRO Technology

XYPRO Technology

XYPRO is the market leader in HPE Non-Stop Security, Risk Management and Compliance.

Directory of Cyber Security Suppliers

Directory of Cyber Security Suppliers

Our Supplier Directory lists 7,000+ specialist cyber security service providers in 128 countries worldwide. IS YOUR ORGANISATION LISTED?

LockLizard

LockLizard

Locklizard provides PDF DRM software that protects PDF documents from unauthorized access and misuse. Share and sell documents securely - prevent document leakage, sharing and piracy.

Chatham House

Chatham House

Chatham House is an independent policy institute based in London. Topics cover foreign affairs and defence including cyber security.

Aves Netsec

Aves Netsec

Aves is a deceptive security system for enterprises who want to capture, observe and mitigate bad actors in their internal network.

GE Digital

GE Digital

GE Digital is a leading software company for the Industrial Internet. Products include Industrial Cyber Security for Operational Technology (OT).

LIFARS

LIFARS

LIFARS is a global leader in Digital Forensics and Cyber Resiliency Services.

Cyjax

Cyjax

Cyjax monitors the Internet to identify the digital risks to your organisation, including cyber threats, reputational risks and the Darknet.

Altaro Software

Altaro Software

Altaro provide backup solutions that are intuitive, easy to use, well-priced and backed by outstanding 24/7 support as part of the package.

Apozy

Apozy

Apozy replaces a secure web gateway to nullify phishing, malware and impersonation attacks.

Propelo

Propelo

Propelo (formerly LevelOps) is an engineering excellence platform that helps increase developer productivity and improve security with data-led insights and workflow automation.

Cobalt Iron

Cobalt Iron

Cobalt Iron is a global leader in SaaS-based enterprise backup and data protection technology.

GRSi

GRSi

GRSi deliver next-generation systems engineering, cybersecurity, technology insertion and best practices-based Enterprise Operations (EOps) management.

HunCERT

HunCERT

HunCERT's mission is to assist Hungarian Internet Service Providers in applying appropriate procedures to address the risks of computer network incidents and to respond to such incidents.

Def-Logix

Def-Logix

Def-Logix was founded in 2008 to help solve cyber threats being experienced by government agencies of the United States.

Elastio

Elastio

Elastio's cloud-native platform safeguards cloud data from the risks posed by ransomware, application failures and storage security vulnerabilities.

Cyberleaf

Cyberleaf

Cyberleaf is simplified managed cybersecurity for MSPs, enabling top tier cyber protection for small and medium enterprise.

HYCU

HYCU

HYCU was born of the need to simplify data protection and provide equivalent levels of backup and recovery support across on premises, public cloud, and SaaS workloads.

Anthropic

Anthropic

Anthropic is a Public Benefit Corporation, whose purpose is the responsible development and maintenance of advanced AI for the long-term benefit of humanity.