Qualcomm Zeroth - brain like processor


Qualcomm Zeroth processor to not only mimic human-like perception but also have the ability to learn how biological brains do.

This might be the powerful new tool for drones development in the next few years. Just imagine what possibilities it gives.

We have a lot of switches on our radio (or tablet). It would be amazing, to use one as a "good drone" button. The speed of learning in a connected network like Mission Planner could be incredible. With this feature the future looks way more futuristic and drone populated.

I would love to order, in few years time, my first 3DR NPU (Neural Processing Unit), wouldn't you? :) 

Look at the video below.

Qualcomm Zeroth processors have three main goals:

1. Biologically Inspired Learning

2. Enable Devices To See and Perceive the World as Humans Do

3. Creation and definition of an Neural Processing Unit—NPU


Qualcomm’s technologies are designed from the ground-up with speed and power efficiency in mind. This way, devices that use our products can run smoothly and maximize battery life driven experiences. As mobile computing becomes increasingly pervasive, so do our expectations of the devices we use and interact with in our everyday lives. We want these devices to be smarter, anticipate our needs, and share our perception of the world so we can interact with them more naturally. The computational complexity of achieving these goals using traditional computing architectures is quite challenging, particularly in a power- and size-constrained environment vs. in the cloud and using supercomputers.

For the past few years our Research and Development teams have been working on a new computer architecture that breaks the traditional mold. We wanted to create a new computer processor that mimics the human brain and nervous system so devices can have embedded cognition driven by brain inspired computing—this is Qualcomm Zeroth processing.

We have three main goals for Qualcomm Zeroth processors:

1. Biologically Inspired Learning

We want Qualcomm Zeroth products to not only mimic human-like perception but also have the ability to learn how biological brains do.  Instead of preprogramming behaviors and outcomes with a lot of code, we’ve developed a suite of software tools that enable devices to learn as they go and get feedback from their environment.

In the video below, we outfitted a robot with a Qualcomm Zeroth processor and placed it in an environment with colored boxes. We were then able to teach it to visit white boxes only. We did this through dopaminergic-based learning, a.k.a. positive reinforcement—not by programming lines of code.

2. Enable Devices To See and Perceive the World as Humans Do

Another major pillar of Zeroth processor function is striving to replicate the efficiency with which our senses and our brain communicate information. Neuroscientists have created mathematical models that accurately characterize biological neuron behavior when they are sending, receiving or processing information. Neurons send precisely timed electrical pulses referred to as “spikes” only when a certain voltage threshold in a biological cell’s membrane is reached. These spiking neural networks (SNN) encode and transmit data very efficiently in both how our senses gather information from the environment and then how our brain processes and fuses all of it together.

3. Creation and definition of an Neural Processing Unit—NPU

The final goal of Qualcomm Zeroth is to create, define and standardize this new processing architecture—we call it a Neural Processing Unit (NPU.) We envision NPU’s in a variety of different devices, but also able to live side-by-side in future system-on-chips. This way you can develop programs using traditional programing languages, or tap into the NPU to train the device for human-like interaction and behavior.  

Read more about this amazing project:




E-mail me when people leave their comments –

You need to be a member of diydrones to add comments!

Join diydrones


  • MR60

    It reminds me my student's final thesis at university where I used neural networks to make a computer learn to recognize tanks' infrared pictures... Aaahh good old times.

    Why do we have to wait 20 years later to read this ? Pfff progress is so slow....(in the open civilian world)


This reply was deleted.