The human brain consumes about 20 watts of power, which is roughly equivalent to a dim light bulb. Despite this low power consumption, it can perform an estimated 10^16 operations per second. In contrast, a high-end Nvidia GPU consumes about 400 watts of power to perform a “measly” 10^14 to 10^15 operations per second. This means the human brain is approximately 100,000 to 1,000,000 times more energy-efficient than modern GPUs.

But what if we could replicate that amazing efficiency on a physical computer chip? That’s the ambitious vision for neuromorphic computing. The neuromorphic computing market, while still in its infancy, is projected to grow by 21.2% annually (CAGR) over the next five years. So in this guide, we’ll explore the top neuromorphic computing stocks, ranked by pure-play focus.

The key growth drivers for the neuromorphic computing market stem from several high-impact sectors.. For example, the automotive industry is pushing for more advanced driver assistance systems and fully autonomous vehicles. These require real-time processing of vast amounts of sensory data with minimal latency and power consumption – an ideal use case for neuromorphic chips. 

Mobile and edge AI is another huge demand driver. As AI capabilities become more important in smartphones and other mobile devices, neuromorphic chips offer a way to run sophisticated AI models without quickly draining batteries or requiring constant cloud connectivity.

That said, keep in the mind that neuromorphic computing is a bleeding edge technology. Creating chips that truly mimic the brain’s neuron and synapse structure at scale is an enormously complex task, and current neuromorphic chips are highly limited in their neuron count compared to the human brain. Also traditional software development approaches don’t translate directly to neuromorphic systems. This presents a major (and still unsolved) challenge in integration with existing computing ecosystems.

Note: We make every effort to keep our info accurate and up-to-date. However, emerging tech moves fast and company situations can change overnight. This guide is an intro to the neuromorphic computing market; but ultimately, do your own due diligence before taking action.

Tier 1: Pure-Play Neuromorphic Computing Stocks

The pure-play neuromorphic computing stocks represent the cutting edge of this nascent industry. These companies stake their entire business model on the potential of these brain-inspired chips. While this focus creates higher risk, it also offers the most direct exposure for investors bullish on neuromorphic computing. With only one public company currently in this tier, it underscores just how early we are in the neuromorphic computing market.

BrainChip Holdings (ASX: BRN)

BrainChip Holdings (ASX: BRN) is a first-mover in commercial neuromorphic computing, with a focus on energy-efficient edge AI.

Australia-based BrainChip is a pioneer in commercializing neuromorphic computing, focusing on edge AI solutions. The company has developed an Edge AI platform that combines innovative silicon IP, software, and machine learning. This platform includes the Akida neuromorphic processor. Akida is designed to process information in a way that mimics the human brain from a fundamental hardware level. This “imitation” goes beyond the deep neural networks used in today’s AI models.

Brainship enjoys first-mover advantage in commercial neuromorphic computing. The company’s technology has several unique features, including microwatt power consumption and on-chip learning, while being able to support standard machine learning workflows. In fact, it offers a claimed 5-10x improvement in performance-per-watt over traditional AI accelerators. This would make the Akida chip ideal for battery-powered devices, edge computing, and in-sensor intelligence.

The company is pursuing a flexible business model centered on high-margin IP licensing. This strategy involves upfront license fees and ongoing royalties, which could provide steady revenue as adoption grows. BrainChip’s intellectual property portfolio includes 17 granted patents and 30 pending patents. The company’s team consists of 80% engineers, with 15% holding PhDs from leading AI research programs. BrainChip is also building partnerships with system integrators, including MegaChips, Prophesee, and SiFive.

Computer Vision AI and self driving cars in a smart city.
Neuromorphic chips are ideal for machine vision, edge AI, and smart cities.

Tier 2: Tech Giants with Neuromorphic Initiatives

This tier features established tech giants making strategy investments in neuromorphic computing. These companies offer a blend of stability and innovation. The neuromorphic projects from these companies benefit from substantial R&D budgets and existing technological ecosystems. However, neuromorphic computing remains a small part of their overall business. This tier reveals how seriously major players view the potential of brain-inspired chips, even if commercialization is still years out.

Intel Corporation (INTC)

Intel (INTC) developed Loihi, a neuromorphic chip with millions of artificial neurons that excels at real-time learning and adaptation.

Intel’s Loihi neuromorphic chip represents a significant advancement in brain-inspired computing. The chip contains millions of artificial neurons and synapses, allowing it to process information in a manner similar to biological neural networks. This architecture enables Loihi to excel at tasks that involve learning and adapting to new information in real-time, a capability that traditional computing systems often struggle with.

One of Loihi’s key features is its energy efficiency. The chip can perform certain types of AI computations using up to 1,000 times less energy than conventional processors. This efficiency stems from its event-driven processing, where neurons only activate when they receive sufficient input, similar to how biological neurons function. This approach allows Loihi to handle complex cognitive tasks while consuming minimal power, making it particularly suitable for edge computing and IoT applications.

Loihi’s versatility has been evident in various research applications. Intel has used the chip to solve optimization problems, control robotic systems, and process sensory data. For example, Loihi has been applied to gesture recognition, real-time image classification, and even olfactory processing. The chip’s ability to learn and adapt quickly has also shown promise in creating AI systems that can operate effectively in dynamic, unpredictable environments. As Intel continues to refine and scale up its neuromorphic technology, Loihi could potentially bridge the gap between traditional computing and the complex, adaptive capabilities of biological brains.

IBM (IBM)

IBM (IBM) created TrueNorth, an energy-efficient neuromorphic chip capable of processing billions of synaptic operations per second per watt.

IBM’s TrueNorth neuromorphic chip architecture represents a significant leap in brain-inspired computing. The chip consists of a network of neurosynaptic cores, each containing 256 neurons that can establish up to 256 connections with other neurons. This dense, interconnected structure allows TrueNorth to process information in a highly parallel manner, similar to biological neural networks. The architecture is particularly adept at handling sensory data and performing pattern recognition tasks.

TrueNorth’s energy efficiency is one of its standout features. The chip can perform complex cognitive tasks while consuming only a fraction of the power required by traditional processors. This efficiency is achieved through its event-driven design, where neurons only activate and consume energy when they receive sufficient input. As a result, TrueNorth can process billions of synaptic operations per second per watt, making it well-suited for deployment in power-constrained environments such as mobile devices and IoT sensors.

IBM has demonstrated TrueNorth’s capabilities in various real-world applications. The chip has been used for tasks such as real-time object recognition, audio processing, and complex data analysis. For instance, TrueNorth has been applied to analyze satellite imagery for disaster response, detect anomalies in financial transactions, and even assist in medical diagnosis. The chip’s ability to learn and adapt to new patterns makes it particularly useful in scenarios where data streams are constantly changing. As IBM continues to develop and scale its neuromorphic technology, TrueNorth could play a crucial role in advancing AI systems that can operate more efficiently and effectively in complex, real-world environments.

Phase Change Neurons for Neuromorphic Computing - IBM
These phase change neurons store states in response to neuronal inputs. Credit: IBM Research

Tier 3: AI Chipmakers with Neuromorphic Research

The final tier consists of AI chip companies exploring neuromorphic principles. These companies provide more indirect exposure to the field. While not fully committed to neuromorphic designs, these companies are incorporating brain-inspired elements into their existing AI hardware. This tier illustrates how the lines between traditional AI acceleration and neuromorphic computing are blurring, potentially leading to hybrid approaches that could accelerate adoption.

Advanced Micro Devices (AMD)

Advanced Micro Devices (AMD) leverages its high-performance computing platforms to support neuromorphic computing research.

AMD, while primarily known for its CPUs and GPUs, could fit neuromorphic computing into its broader AI strategy. Keep in mind though, AMD’s current approach to neuromorphic computing is not publicized. The company is still focused more on general-purpose AI acceleration rather than specialized neuromorphic hardware. That said, there are natural synergies.

For example, AMD’s Instinct accelerators, designed for high-performance computing and AI, provide a platform for researchers to experiment with neuromorphic algorithms. While not strictly neuromorphic, these accelerators offer the power and flexibility needed to simulate large-scale spiking neural networks.

AMD has also developed software tools that could support neuromorphic computing research. For example, The company’s ROCm (Radeon Open Compute) platform includes libraries for deep learning and scientific computing that can be adapted for neuromorphic simulations.

Nvidia (NVDA)

Nvidia (NVDA) incorporates brain-inspired principles into its AI hardware and software stack, supporting efficient spiking neural networks.

Nvidia, known mainly for its GPUs, could also easily fit in neuromorphic computing as part of its broader AI strategy. Nvidia’s approach differs from the more specialized neuromorphic chips developed by Intel and IBM. Instead, Nvidia has been incorporating brain-inspired principles into its AI hardware and software stack.

For example, Nvidia has focused on developing hardware accelerators that can efficiently run spiking neural networks (SNNs). These networks are designed to more closely mimic the way biological neurons communicate, using discrete spikes of activity rather than continuous signals. This has allowed researchers to experiment with neuromorphic algorithms on widely available hardware.

In addition to hardware support, Nvidia has also developed software tools to facilitate neuromorphic computing research. The company’s CUDA Deep Neural Network library (cuDNN) has been extended to support sparse and event-driven computations. These types of computations are highly characteristic of neuromorphic systems. As AI continues to evolve, Nvidia will likely play a major role in bridging traditional deep learning approaches with more brain-like computing paradigms.

Qualcomm (QCOM)

Qualcomm (QCOM) is an early adopter of neuromorphic computing principles, influencing the development of its NPUs for mobile devices.

Qualcomm has been an early adopter of neuromorphic computing principles, with its efforts dating back to the Zeroth project. This initiative, launched in the early 2010s, aimed to develop a brain-inspired computing platform for mobile devices. The Zeroth chip was designed to process sensory data more efficiently by mimicking the human brain’s information processing methods.

Zeroth incorporated artificial neurons and synapses, creating a more brain-like processing architecture. This approach was intended to enable more natural and efficient handling of tasks like image recognition, speech processing, and other forms of sensory data analysis. One of the key goals was to create AI systems that could learn and adapt in real-time, similar to biological brains

The learnings from the Zeroth project have likely influenced Qualcomm’s ongoing AI and machine learning initiatives, particularly in the development of their Neural Processing Units (NPUs) for mobile devices. These NPUs, now integrated into Qualcomm’s mobile system-on-chip (SoC) designs, are designed to handle AI workloads more efficiently than traditional CPU or GPU architectures. While not fully neuromorphic, these NPU designs incorporate brain-inspired principles.

Private Neuromorphic Companies to Watch

Neuromorphic computing is an incredibly young field, and many of the most promising startups are still private. In addition to BrainChip (which is already public), we cover five other innovative startups—SynSense, GrAI Matter Lab, Prophesee, Innatera, and MemComputing—on this page.