Researchers and companies are running a race to create technology that is identical to humans and their neural systems. The concept of neuromorphic computing emulating the neural structure of the human brain emerged from endless efforts. While the first generation of AI was rule-based and imitated classical logic to draw reasoned conclusions without a specific, narrowly defined problem domain, the current generation is moving to a more sophisticated form of human cognition with neuromorphic technology. Neuromorphic engineering concerns mechanisms that could fit compactly in a small space, unlike most supercomputers, which fill rooms. The neuromorphic computing market is valued at US$22,743 thousand in 2021 and is anticipated to reach US$550,593 thousand by 2026 with a CAGR of 89.1% during the forecast period. As the importance of neuromorphic technology is brought to light, more start-ups are jumping into the less explored space to try their technological supremacy. Analytics Insight has listed the top 10 neuromorphic computing start-ups that are developing innovative solutions for neuromorphic engineering.
Innatera Nanosystems is a Dutch company and an offspring of the Delft University of Technology in the Netherlands. Innatera provides next-generation neuromorphic intelligence for the sensor edge. The company's ultra-efficient neuromorphic processors mimic the brain's mechanisms for processing sensory data. Innatera processors leverage the computing capabilities of spiking neural networks to deliver ground-breaking cognition performance within a narrow power envelope based on a proprietary analog-mixed signal computing architecture. With an ultimate combination of ultra-low power consumption and short response latency, the devices enable high-performance always-on pattern recognition capabilities in applications at the sensor edge. In 2020, the company raised 5 million Euros to bring its brain-inspired processing technology to sensors and sensor-based devices.
Koniku Kore is the Nigerian start-up that was the first to fuse live neurons from mice stem cells into a silicon chip. The start-up merged synthetic neurobiology with traditional silicon technology to reach the goal of fixing urgent real-world problems. Koniku leverages a platform technology for Neurogrammers with applications like neurons & connections in 3D, multiple neuron types within/out channels and any receptor type- from the factory or in the field. Koniku's devices are being used for defense, security, drug development, and control. The start-up is also developing advanced sensors with Boeing and building chips to accurately model plaque transportation in Alzheimer's for AstraZeneca.
INSTAR Robotics is an autonomous mobile robot maker that supplies robots for logistics and agriculture. The start-up designs robots to be useful to humans by reducing repetitive and uninteresting tasks. The highlight of INSTAR Robotics is that the start-up uses neuro-inspired robots to streamline agriculture processes. The robots use neural network algorithms designed with cognitive capabilities to communicate with their surroundings and make decisions based on that. Besides, the robots don't require any training or human intrusion upon installation at agricultural logistics and plant nurseries.
iniLabs incubates neuromorphic technologies. The start-up founders have invented some of the key foundations of the field and iniLabs now continues to lead the world in neuromorphic engineering through its close collaboration with the Institute of Neuroinformatics at the University of Zurich and the ETH Zurich. iniLabas has also powered over 500 labs and companies with its spin-off technologies around the world in industries including aerospace, automotive, consumer electronics, industry vision, and security. The start-up also conducts student projects on neuromorphic computing.
Nervana System focuses on building technology to power the next generation of intelligent applications. The start-up used deep learning and neural networks to provide a full-stack software-as-a-service platform the enables businesses to develop custom deep learning software. In 2016, Intel has announced the acquisition of Nervana Systems to extend its capabilities in deep neural networks used in artificial intelligence applications. Intel was intended to use Nervana's accelerator and software that is tailored to use a more general-purpose GPU to do the heavy lifting.
SynSense is a neuromorphic computing company that provides dedicated mixed-signal neuromorphic processors that overcome the limitations of legacy von Neumann computers to leverage an unprecedented combination of ultra-low power consumption and low latency performance. Founded in 2017, the start-up is based on advances in neuromorphic computing hardware developed at the Institute of Neuroinformatics of the University of Zurich and ETH Zurich. SynSense has a unique technological edge and IP portfolio that comes from over 20 years of experience in mixed-signal neural processor design, advanced neural routing architectures, and neural algorithms.
BrainChip is a new global technology company that is setting new standards for artificial intelligence at the edge. The start-up is revolutionizing Edge AI applications with its event domain neural processor and comprehensive development environment. In 2018, the leading neuromorphic computing company established itself as the first company to bring a production spiking neural network architecture called Akida Neuromorphic System-on-Chip (NSoC) to market. BrainChip's Akida hardware and software products are the result of over a decade of fundamental R&D by the company's engineers and data scientists.
GrAI Matter Labs is a pioneer of ultra-low power neuromorphic computing that utilizes biology-inspired spiking neural networks to overcome the limitations of traditional Von Neumann machines and application processors. The start-up develops a neuromorphic computing architecture for sensor analytics and machine learning, inspired by biological brain. In November 2020, GrAI Matter Labs has raised US$14 million in funding, which the company said will be used to accelerate the design and market launch of its first GrAI full-stack AI system-on-chip platform, to deliver on customer needs at the edge.
Intrinsic Semiconductor Technologies is established to develop silicon-based RRAM technologies. The start-up aims to deliver a non-volatile memory that can not only be easily integrated on the same chip that is doing the computation, but at the memory that is faster, cheaper, and lowers energy than the Flash memory we use today. In 2021, the start-up closed a 1.35 million Euro seed funding round led by investors UCL Technology Fund and IP Group plc. The funding was assigned to enable Instrinsic to disrupt the US$60 billion non-volatile memory market by partnering with leading semiconductor research foundry, imec in Belgium to develop prototypes.
MemComputing Inc has developed disruptive technology that is changing the face of computing through a SaaS solution that improves the performance of machine learning/optimization calculations by four orders of magnitude. Founded in 2012, the start-up performs both the task of storing and processing information vs currency computers that follow the von Neumann architecture where memory and processing are separate. In 2020, MemComputing released its whitepaper entitled 'An Efficient Approach to the Supervised Training of Deep Neural Networks using MemComputing,' highlighting the advantages of MemComputing's new training approach compared to traditional deep learning methods.
Join our WhatsApp Channel to get the latest news, exclusives and videos on WhatsApp
_____________
Disclaimer: Analytics Insight does not provide financial advice or guidance. Also note that the cryptocurrencies mentioned/listed on the website could potentially be scams, i.e. designed to induce you to invest financial resources that may be lost forever and not be recoverable once investments are made. You are responsible for conducting your own research (DYOR) before making any investments. Read more here.