What if every time you learned something new, you forgot a little of what you knew before? That sort of overwriting doesn’t happen in the human brain, but it does in artificial neural networks. It’s appropriately called catastrophic forgetting. So why are neural networks so successful despite this? How does this affect the future of things like self-driving cars? Just what limit does this put on what neural networks will be able to do, and what’s being done about it?
Numerical weights in an artificial neural network
Neurons in the brain
The way a neural network stores knowledge is by setting the values of weights (the lines in between the neurons in the diagram). That’s what those lines literally are, just numbers assigned to pairs of neurons. They’re analogous to the axons in our brain, the long tendrils that reach out from one neuron to the dendrites of another neuron, where they meet at microscopic gaps called synapses. The value of the weight between two artificial neurons is roughly like the number of axons between biological neurons in the brain.
To understand the problem, and the solutions below, you need to know a little more detail.
Artificial Intelligence is playing an ever increasing role in the lives of civilized nations, though most citizens probably don’t realize it. It’s now commonplace to speak with a computer when calling a business. Facebook is becoming scary accurate at recognizing faces in uploaded photos. Physical interaction with smart phones is becoming a thing of the past… with Apple’s Siri and Google Speech, it’s slowly but surely becoming easier to simply talk to your phone and tell it what to do than typing or touching an icon. Try this if you haven’t before — if you have an Android phone, say “OK Google”, followed by “Lumos”. It’s magic!
Advertisements for products we’re interested in pop up on our social media accounts as if something is reading our minds. Truth is, something is reading our minds… though it’s hard to pin down exactly what that something is. An advertisement might pop up for something that we want, even though we never realized we wanted it until we see it. This is not coincidental, but stems from an AI algorithm.
At the heart of many of these AI applications lies a process known as Deep Learning. There has been a lot of talk about Deep Learning lately, not only here on Hackaday, but all over the interwebs. And like most things related to AI, it can be a bit complicated and difficult to understand without a strong background in computer science.
If you’re familiar with my quantum theory articles, you’ll know that I like to take complicated subjects, strip away the complication the best I can and explain it in a way that anyone can understand. It is the goal of this article to apply a similar approach to this idea of Deep Learning. If neural networks make you cross-eyed and machine learning gives you nightmares, read on. You’ll see that “Deep Learning” sounds like a daunting subject, but is really just a $20 term used to describe something whose underpinnings are relatively simple.
Neural networks are all the rage right now with increasing numbers of hackers, students, researchers, and businesses getting involved. The last resurgence was in the 80s and 90s, when there was little or no World Wide Web and few neural network tools. The current resurgence started around 2006. From a hacker’s perspective, what tools and other resources were available back then, what’s available now, and what should we expect for the future? For myself, a GPU on the Raspberry Pi would be nice.
Tech artist [Alexander Reben] has shared some work in progress with us. It’s a neural network trained on various famous peoples’ speech (YouTube, embedded below). [Alexander]’s artistic goal is to capture the “soul” of a person’s voice, in much the same way as death masks of centuries past. Of course, listening to [Alexander]’s Rob Boss is no substitute for actually watching an old Bob Ross tape — indeed it never even manages to say “happy little trees” — but it is certainly recognizable as the man himself, and now we can generate an infinite amount of his patter.
Behind the scenes, he’s using WaveNet to train the networks. Basically, the algorithm splits up an audio stream into chunks and tries to predict the next chunk based on the previous state. Some pre-editing of the training audio data was necessary — removing the laughter and applause from the Colbert track for instance — but it was basically just plugged right in.
The network seems to over-emphasize sibilants; we’ve never heard Barack Obama hiss quite like that in real life. Feeding noise into machines that are set up as pattern-recognizers tends to push them to the limits. But in keeping with the name of this series of projects, the “unreasonable humanity of algorithms”, it does pretty well.
He’s also done the same thing with multiple speakers (also YouTube), in this case 110 people with different genders and accents. The variation across people leads to a smoother, more human sound, but it’s also not clearly anyone in particular. It’s meant to be continuously running out of a speaker inside a sculpture’s mouth. We’re a bit creeped out, in a good way.
We’ve covered some of [Alexander]’s work before, from the wince-inducing “Robot Bites Man” to the intellectual-conceptual “All Prior Art“. Keep it coming, [Alexander]!
The last year has been great for Nvidia hardware. Nvidia released a graphics card using the Pascal architecture, 1080s are heating up server rooms the world over, and now Nvidia is making yet another move at high-performance, low-power computing. Today, Nvidia announced the Jetson TX2, a credit-card sized module that brings deep learning to the embedded world.
The Jetson TX2 is the follow up to the Jetson TX1. We took a look at it when it was released at the end of 2015, and the feelings were positive with a few caveats. The TX1 is still a very fast, very capable, very low power ARM device that runs Linux. It’s low power, too. The case Nvidia was trying to make for the TX1 wasn’t well communicated, though. This is ultimately a device you attach several cameras to and run OpenCV. This is a machine learning module. Now it appears Nvidia has the sales pitch for their embedded platform down.
The concept of artificial intelligence dates back far before the advent of modern computers — even as far back as Greek mythology. Hephaestus, the Greek god of craftsmen and blacksmiths, was believed to have created automatons to work for him. Another mythological figure, Pygmalion, carved a statue of a beautiful woman from ivory, who he proceeded to fall in love with. Aphrodite then imbued the statue with life as a gift to Pygmalion, who then married the now living woman.
Throughout history, myths and legends of artificial beings that were given intelligence were common. These varied from having simple supernatural origins (such as the Greek myths), to more scientifically-reasoned methods as the idea of alchemy increased in popularity. In fiction, particularly science fiction, artificial intelligence became more and more common beginning in the 19th century.
But, it wasn’t until mathematics, philosophy, and the scientific method advanced enough in the 19th and 20th centuries that artificial intelligence was taken seriously as an actual possibility. It was during this time that mathematicians such as George Boole, Bertrand Russel, and Alfred North Whitehead began presenting theories formalizing logical reasoning. With the development of digital computers in the second half of the 20th century, these concepts were put into practice, and AI research began in earnest.
Over the last 50 years, interest in AI development has waxed and waned with public interest and the successes and failures of the industry. Predictions made by researchers in the field, and by science fiction visionaries, have often fallen short of reality. Generally, this can be chalked up to computing limitations. But, a deeper problem of the understanding of what intelligence actually is has been a source a tremendous debate.
Despite these setbacks, AI research and development has continued. Currently, this research is being conducted by technology corporations who see the economic potential in such advancements, and by academics working at universities around the world. Where does that research currently stand, and what might we expect to see in the future? To answer that, we’ll first need to attempt to define what exactly constitutes artificial intelligence.