Lifelong Deep Neural Networks

There are three main ingredients needed for intelligent robots to be ubiquitous, smart, and useful. I like to call these three ingredients Mind, Brain, and Body. Let’s look at how these three enabling technology have evolved, and why the time is now for the emergent of intelligent machines.

Body is the easy one: robots need to be cheaply produced. This is happening thanks to innovations in rapid prototyping, 3D printing, and plummeting cost of sensors due to massive adoption of mobile devices, which contain much of the sensors robots need.

Mind is what Neurala does: we design the software to make these robots learn and behave (perceive, navigate) intelligently. We pioneered Deep Learning algorithms (before they were Deep… they were called ‘Neural’ networks!), and make them work on robots and drones.

However, Body and Mind alone are hopeless without what I call the Brain. By Brain I refer not to algorithms, or intelligent per se, but to computing substrate that can run a Mind in real-time on a Body.

Not all computing substrates, of course, fit the bill. We need low-power, yet powerful (in terms of computing density, this can be summarized as GFLOP/Watt) processors that can be fit on a mobile platform. See our article on IEEE Spectrum on this topic.

In a sense, this is nothing different than a cooking recipe for a good pizza Margherita! All you need is thee ingredients need to be present simultaneously, and be of good quality, to enable unlocking of robot potential: inexpensive Body, intelligent Mind, and powerful (yet not power-hungry!) Brain.

What has really changed in the past few years, and is really the underlying success of many of the progress done by Artificial Intelligence in the past few years, including the recent success (almost viral) of Deep Networks, is that hardware now exist that can support a Mind. Let’s look at this hardware more in details.

Minds, in particular Deep (Neural) Networks, are algorithms whose execution and training methods are highly conducive to parallelism. Graphic processing units (GPUs), originally designed for computer gaming and 3D graphic processing, have been used in general-purpose, computationally intensive models in application domains ranging from physical modeling, image processing, and computational intelligence since early 2000’s. More recently, fast-moving startups such as Movidius have introduced a different framework, called visual processing unit (VPU- a term also occasionally associated with GPUs), which provides another quantum leap into the battle between the two opposing “gods”: GFLOP and Watt. More on VPU later: let’s start with GPU.

The term GPGPU is often used to refer to the backbone of the revolution: General-Purpose computation on Graphics Processing Units. GPUs, chips whose main technological push come from huge revenues from the gaming market, and more recently are finding their ways into mobile devices, are in reality high-performance many-core processors that can be used to accelerate a wide range of applications, going from physics, to chemistry, to computer vision, to neuroscience. And, of course, Deep Networks for robotics and other applications.

GPU-accelerated computing leverages GPUs to reduce the time in computing complex applications: it offloads compute-intensive portions of the application to the GPU, while the remainder of the code still runs on the CPU. An intuitive way to understand why this is faster is to look into how CPU and GPU compute: while CPU are designed to have a few cores optimized for sequential serial processing, GPUs have been built by design as massively parallel processors consisting of thousands of smaller cores which are best at handling multiple tasks simultaneously.

Neurala itself started in 2006 as a container for a patent to use GPUs are general purpose Neural simulator: we realized very quickly, back in early 2000’s, that GPU were going to change the game of AI and make it real not only for big companies, but for everyday uses and consumers.

It was a cold and rainy winter in 2004, when Anatoli Gorchetchnikov, Heather Ames and myself got really interested in general purpose computing on graphic processing cards. At the time, there was no CUDA or OpenGL available: programming GPUs was really tough. I call that “BC” (Before Cuda) times…But we tried, with some very good results, to port some of the models we used on GPUs. It was so good that we wrote a patent around that work, and we created a company, Neurala, to contain it. Years later, the company has raised money, entered TechStars, and launching products, but this is yet another story!

First of all, a disclaimer: the GeForceR 6800 used at the time is today a museum piece…nevertheless, many of the arguments that follow are still relevant.

As you may have heard, Deep Networks or Artificial Neural Networks (ANNs) are highly parallel, computationally intensive mathematical models that capture the dynamics and adaptability of biological neurons. Neurons are cells that make up most of the nervous system. An adult human brain weights approximately 1.3 Kg and includes 100 billion neurons. The neuron’s axon then communicates signals to other neurons (approximately, each neuron is connected to other 10,000 neurons).

The artificial counterparts of biological neurons are dynamical systems requiring numerical integration to calculate their variables at every moment of time as a function of previous values of one or more of these variables. In certain classes of ANNs, neurons are described in terms of complex system of differential equations, and a significant degree of recurrency can characterize their connectivity matrix. Graphic processing units (GPUs), originally designed for computer gaming and 3D graphic processing, have been used in general-purpose, computationally intensive models in application domains ranging from physical modeling, image processing, and computational intelligence. Biologically realistic neural networks are used to model brain areas responsible for perceptual, cognitive, and memory functions. You can read more details in this post.

Of course, the roots of the theory and GPU computation go really deep in the past. How Deep in the past? And how Deep in the past go the theories that are the backbones of the recent surge in popularity of these algorithms? Jürgen Schmidhuber (Pronounce: You_again Shmidhoobuh), a professor at IDSIA in Lugano, Switzerland, provides a great historical survey which summarizes how the Deep Network field origins go back to the previous millennium. He is right: Deep Networks are the results of the combination, permutation, mutation, and refinements of algorithms that have been researched and fielded in the past few decades.

However, the introduction of constantly smaller/more power efficient GPUs is changing the range of applicability of these technologies. Recently, the main player in GPU, nVidia, unveiled the release of the NVIDIA Jetson TX1 Developer Kit, a mobile GPU which, in my opinion, will be a game-changer in enabling more portable and ubiquitous artificial intelligence applications, from mobile robots to drones.

Smaller GPU, bigger Drones/Robotic markets. As simple as that.

Now, what about the VPU (visual processing unit?).

VPU differs from GPUs as they were designed from the ground-up to allow mobile devices to process intensive computer vision algorithms (whereas GPUs were adapted from processing graphics to machine vision). For instance, Movidius has developed and ad-hoc chip architecture to greatly optimize the GFLOP vs. Watt “fight”. Their Myriad 2 is the industry’s first always-on vision processor. In a sense, GPUs were the beginning, but they may not be the end of where “brain” computing is going, and companies like Movidius will surely push the boundaries of what can be done by introducing new computing frameworks.

It’s a good time to be around, with several forces pushing simultaneously to solve the Mind, Brain, and Body problem, every resistance is futile.

179 thoughts on “Deep Learning, GPUs, VPUs, and cheap bodies: three ingredients for ubiquitous intelligent robotics”
  1. Thank you for your entire labor on this web site. My mom take interest in managing investigations and it is obvious why. My partner and i learn all regarding the lively tactic you produce simple things through your web site and in addition invigorate response from the others on the situation then our favorite princess is truly studying a whole lot. Take advantage of the rest of the year. You have been doing a superb job.

  2. My husband and i felt now excited Emmanuel could conclude his inquiry from your ideas he gained in your site. It’s not at all simplistic just to choose to be giving for free ideas that most people have been making money from. And we all do understand we have the website owner to be grateful to because of that. The explanations you’ve made, the easy site menu, the friendships you can give support to engender – it’s everything extraordinary, and it’s facilitating our son and our family do think that idea is cool, and that is highly important. Many thanks for all the pieces!

  3. I simply wished to thank you very much yet again. I do not know what I would have used without those tips and hints shown by you relating to this theme. This has been the traumatic setting in my view, nevertheless viewing your well-written way you treated the issue took me to weep with joy. Now i am thankful for your work as well as wish you recognize what an amazing job your are undertaking training the others with the aid of your website. Probably you haven’t met any of us.

  4. Bạn có biết các giống mèo hiện nay chưa. Mèo là vật nuôi được nhiều người ưa chuộng nhất hiện nay. Tuy nhiên khách hàngcòn chưa có đủ học tập để phân biệt các giống mèo. Việc lựa chọn một chú mèo về làm thú cưng không đơn thuần chỉ là mua và bán nếu bạn không hiểu tính tình và lối sống của chúng thì chắc chắn rằng chúng sẽ bị bệnh ngay lập tức.

  5. Right here is the perfect site for everyone who really wants to find out about this topic.

    You realize a whole lot its almost hard to argue with
    you (not that I really would want to…HaHa).
    You definitely put a new spin on a topic that has been written about for many years.
    Excellent stuff, just great!

  6. I blog often and I really appreciate your information. This article has truly
    peaked my interest. I will bookmark your site and keep checking for new details about once a week.
    I subscribed to your RSS feed as well.

  7. It’s perfect time to make a few plans for the
    longer term and it’s time to be happy. I’ve learn this put up and
    if I may just I desire to suggest you few fascinating things or tips.
    Maybe you can write subsequent articles referring to this article.
    I want to learn even more things about it!

  8. It’s the best time to make some plans for the future
    and it is time to be happy. I’ve learn this publish and if I may just I want to counsel you few
    fascinating things or advice. Maybe you could write
    next articles referring to this article. I wish to read more issues
    about it!

  9. I’ve been surfing online more than three hours these days, yet I never discovered any
    interesting article like yours. It is beautiful worth sufficient for me.
    In my opinion, if all webmasters and bloggers made excellent content material as you did,
    the web shall be a lot more useful than ever before.

  10. I will right away take hold of your rss as I
    can not to find your email subscription hyperlink or newsletter service.
    Do you have any? Please let me understand so that I may just subscribe.

  11. Howdy just wanted to give you a quick heads up.
    The words in your content seem to be running off the screen in Internet explorer.

    I’m not sure if this is a format issue or something to do with internet browser compatibility but I thought I’d post to let you
    know. The design and style look great though! Hope you get
    the problem fixed soon. Thanks

  12. I have been browsing online more than 4 hours today, yet I
    never found any interesting article like yours. It is pretty worth enough
    for me. In my view, if all webmasters and bloggers made good content
    as you did, the net will be much more useful than ever

  13. It’s the best time to make a few plans for the long run and
    it is time to be happy. I have read this put up and if I could
    I want to suggest you some attention-grabbing things or advice.

    Maybe you can write subsequent articles relating to this article.

    I desire to read even more issues about it!

  14. It’s perfect time to make a few plans for the longer term and
    it is time to be happy. I’ve learn this publish and if I may I want to suggest you some fascinating issues or suggestions.
    Maybe you can write next articles relating to
    this article. I want to learn even more issues about it!

Leave a Reply

Your email address will not be published.

I accept that my given data and my IP address is sent to a server in the USA only for the purpose of spam prevention through the Akismet program.More information on Akismet and GDPR.