Theoretical physicists from ETH Zurich deliberately misled intelligent machines, and thus refined the process of machine learning. They created a new method that allows computers to categorise data – even when humans have no idea what this categorisation might look like.
When computers independently identify bodies of water and their outlines in satellite images, or beat the world’s best professional players at the board game Go, then adaptive algorithms are working in the background. Programmers supply these algorithms with known examples in a training phase: images of bodies of water and land, or sequences of Go moves that have led to success or failure in tournaments.
Similarly to how our brain nerve cells produce new networks during learning processes, the special algorithms adapt in the learning phase based on the examples presented to them. This continues until they are able to differentiate bodies of water from land in unknown photos, or successful sequences of moves from unsuccessful ones.
Graphic: iStock / AcidLabs
Until now, these artificial neural networks have been used in machine learning with a known decision-making criterion: we know what a body of water is and which sequences of moves were successful in Go tournaments.
Now, a group of scientists working under Sebastian Huber, Professor of Condensed Matter Theory and Quantum Optics at ETH Zurich, have expanded the applications for these neural networks by developing a method that not only allows categorisation of any data, but also recognises whether complex datasets contain categories at all.
Questions of this kind arise in science: for example, the method could be useful for analysis of measurements from particle accelerators or astronomical observations. Physicists could thus filter out the most promising measurements from their often unmanageable quantities of measurement data. Pharmacologists could extract molecules with a certain probability of having a specific pharmaceutical effect or side-effect from large molecular databases. And data scientists could sort huge masses of disordered data ripples and obtain usable information (data mining).
Syrup droplets and water mix over time: they reach a state of equilibrium in which it is no longer possible to say where the syrup droplet was located initially. In quantum physics, however, some systems remember their initial state forever. Physicists refer to this as many-body localisation.
In order to locate this boundary, the scientists developed the “act as if” principle: taking data from quantum systems, they established an arbitrary boundary based on one parameter and used it to divide the data into two groups. They then trained an artificial neural network by pretending to it that one group reached a state of equilibrium while the other did not. Thus, the researchers acted as if they knew where the boundary was.
They trained the network countless times overall, with a different boundary each time, and tested the network’s ability to sort data after each session. The result was that, in many cases, the network struggled to classify the data as the scientists had. But in some cases, the division into the two groups was very accurate.
The researchers were able to show that this sorting performance depends on the location of the boundary. Evert van Nieuwenburg, a doctoral student in Huber’s group, explains this as follows: “By choosing to train with a boundary far away from the actual boundary (which I don’t know), I am able to mislead the network. Ultimately we’re training the network incorrectly – and incorrectly trained networks are very bad at classifying data.”
The researchers also demonstrated the capabilities of their new method using two further questions from theoretical physics: topological phase transitions in one-dimensional solids and the Ising model, which describes magnetism inside solids.
The new method can also be illustrated in simplified form with a thought experiment, where we want to classify red, reddish, bluish and blue balls into two groups. We assume that we have no idea of how such a classification might reasonably look.
If a neural network is trained by telling it that the dividing line lies somewhere in the red region, then this will confuse the network. “You try to teach the network that blue and reddish balls are the same and ask it to differentiate between red and red balls, which it simply isn’t able to do,” says Huber.
On the other hand, if you place the boundary in the violet colour spectrum, the network learns an actual difference and sorts the balls into red and blue groups. However, one does not need to know in advance that the dividing line should be in the violet region. By comparing the sorting performance at a variety of chosen boundaries, this boundary can be found with no prior knowledge.
Tanks on Move Near Oroville Dam - Big Story Unfolding
Time Is Running Out Fast: Are You Ready for What's Coming? Why Isn't Anyone Talking About This?! (Videos) Mr Doom, Jason A
The Impossible Event that Changed the World - Everybody Needs to Be Talking About This - New Jason A Video
11 Facts That Prove That the U.S. Economy in 2017 Is in Far Worse Shape Than it Was in 2016
X22Report Event of All Events, the Day When the Lights Go Out - Episode 1261b
Mainstream Media Gets Caught in its Own Snare! Classic!
Pedogate: Former Trump Campaign Manager Judge Tim Nolan Indicted on Sexual Trafficking Charges (Video)
French Embrace Rothschild Status Quo
Did Russia Shoot Down US Missiles in Syria? - Dr. Theodore Karasik Interview Video
Goodbye U.S.S.R and Hello U.S.S.A. (Video)
French Elections – Dollar index – Gold – Silver Trading
The North Korea Weapon Everyone Is Ignoring: VX
Could This Be the Root Cause of Inflammation and Many Modern Diseases?
US Pilot Ejects From Jet Approaching Carrier Headed for Korean Peninsula
This Doctor Delivers the Best Explanation and Treatment for Alzheimer’s
Car Dragged by Truck for Miles, Truck Driver Oblivious
York police say 104 men arrested as part of child sex trafficking probe
Berkeley Co. deputies release dash cam video in fatal motorcycle pursuit
This map shows what $100 is actually worth in your state
Ron Paul Attacked by the CATO Institute - Claims He's Not a Libertarian
French Elections – Dollar index – Gold – Silver Trading
Alex Jones - HD Commercial Free - Sunday (4-23-17)
Ex CIA Robert David Steele On The Political Pedophilia Epidemic
Depopulation Control | Is The Time Of Pregnancy Being Reduced In Modern Era? – Dangerous Premature Birth Rates Point To A Shocking Humanitarian Decline
X22Report Bubbles Are Popping, Prepare For Collapse - Episode 1261a
Major Prophetic Warnings: ‘Socially Accepted But Immoral Lifestyles’ In The Church Will Be Exposed And ‘Judgment Starts Now’
Heads Way the Hell Up! German Courts Legalized the Rape of Citizens by Freaking Immigrants! (Video)
23 Russian Soldiers Killed by an Alien Entity