Summary: If Deep Learning is powered by 2nd generation neural nets. What will the 3rd generation look like? What new capabilities does that imply and when will it get here?
By far the fastest expanding frontier of data science is AI and specifically the rapid advances in Deep Learning. Advances in Deep Learning have been dependent on artificial neural nets and especially Convolutional Neural Nets (CNNs). In fact our use of the word “deep” in Deep Learning refers to the fact that CNNs have large numbers of hidden layers. Microsoft recently won the annual ImageNet competition with a CNN comprised of 152 layers. Compare that with the 2, 3, or 4 hidden layers that are still typical when we use ordinary back-prop NNs for traditional predictive analytic problems.
Two things are happening.
What’s Wrong with CNNs?
The limitations of CNNs have been understood for some time but we’ve been getting such good returns for the last two years it’s been easy to overlook them.
Where Are 3rd and 4th Gen NNs Coming From?
The simple answer is academia but the more interesting answer is from brain research. AI that mimics the way the brain functions is labeled ‘strong’ AI, while AI that doesn’t worry too much about the exact model but gets the same results is called ‘weak’. We recently argued that since the ‘weak’ school has been in transcendence with CNNs that we should find a more dignified and instructive name like ‘engineered’ AI.
What’s most revealing about 3rd and 4th gen NNs is that they are coming from the very research labs that are attempting to reveal exactly how neurons and synapses collaborate within the brain. What was very slow progress for a long time is now experiencing major breakthroughs.
There are many of these modeled-brains underway and if you’d like to see a very impressive demonstration, actually from 2013, see this YouTube video of ‘Spaun’ created by Chris Eliasmith at the University of Waterloo that remembers, and learns unsupervised from its environment.
So the ‘strong’ school looks like it is not only making a comeback but will in fact dominate in the future. We’ll describe the 3rd gen in a minute. The 4th gen that doesn’t yet exist does already have a name. These will be ‘neurophasic’ nets or more likely just brains on a chip.
3rd Gen Spiking Neural Nets (SNNs)
Spiking Neural Nets (SNNs) (also sometimes called Oscillatory NNs) are being developed from an examination of the fact that neurons do not constantly communicate with one another but rather in spikes of signals. We all have heard of alpha waves in the brain and these oscillations are only one manifestation of the irregular cyclic and spiking nature of communication among neurons.
So if individual neurons are activated only under specific circumstances in which the electrical potential exceeds a specific threshold, a spike, what might be the implication for designing neural nets? For one, there is the fundamental question of whether information is being encoded in the rate, amplitude, or even latency of the spikes. It appears this is so.
The SNNs that have been demonstrated thus far show the following characteristics:
What we can observe in the early examples is this:
A final example from a local stealth-mode startup using advanced SNNs. When the SNN was shown a short video of cars moving on a highway it rapidly evolved a counting function. It wasn’t told what its purpose was. It wasn’t told what a car looked like. The images (the data) were moving in an organized but also somewhat chaotic manner. A few minutes later it started to count.
About the author: Bill Vorhies is Editorial Director for Data Science Central and has practiced as a data scientist and commercial predictive modeler since 2001. He can be reached at:
Posted 1 March 2021
© 2021 TechTarget, Inc.
Powered by
Badges | Report an Issue | Privacy Policy | Terms of Service
Most Popular Content on DSC
To not miss this type of content in the future, subscribe to our newsletter.
Other popular resources
Archives: 2008-2014 | 2015-2016 | 2017-2019 | Book 1 | Book 2 | More
Most popular articles
You need to be a member of Data Science Central to add comments!
Join Data Science Central