Statistician raises red flag about reliability of machine learning techniques

Machine learning is everywhere in science and technology: powering facial recognition, picking your recommendations on Netflix, and controlling self-driving cars. But how reliable are machine learning techniques really? A statistician says that the answer is “not very,” arguing that questions of accuracy and reproducability of machine learning have not been fully addressed.

Dr Genevera Allen, associate professor of statistics, computer science, and electrical and computer engineering Rice University in Houston, Texas has discussed this topic at a press briefing and at a scientific conference, the 2019 Annual Meeting of the American Association for the Advancement of Science (AAAS). She warned that researchers in the field of machine learning have spent so much time developing predictive models that they have not devoted enough attention to checking the accuracy of their models, and that the field must develop systems which can assess the accuracy of their own findings.

“The question is, ‘Can we really trust the discoveries that are currently being made using machine-learning techniques applied to large data sets?'” Allen said in a statement. “The answer in many situations is probably, ‘Not without checking,’ but work is underway on next-generation machine-learning systems that will assess the uncertainty and reproducibility of their predictions.”

As an example, recently machine learning has been used to study patients with cancer. To study the disease, scientists use machine learning to identify genetically similar individuals so that drug therapies can then be targeted to these specific genomes. But when comparing across different studies, the clusters identified by machine learning are completely different from each other.

The problem is that machine learning techniques do not have a way to say “I don’t know” or “It’s not clear.” The techniques will generally always produce an answer — in the example of the cancer patients, they will always identify a group in some way — but this answer may not be as certain or accurate as it is believed to be. The techniques are able to find a pattern that exists in the data set, even if only dimly, but the pattern may not hold in the real world.

“There is general recognition of a reproducibility crisis in science right now,” Allen told BBC News. “I would venture to argue that a huge part of that does come from the use of machine learning techniques in science.”

Emerging Tech

A.I.-generated text is supercharging fake news. This is how we fight back

A new A.I. tool is reportedly able to spot passages of text written by algorithm. Here's why similar systems might prove essential in a world of fake news created by smart machines.
Computing

Nvidia’s A.I. Playground lets you edit photos, experience deep learning research

Nvidia is making it easier to access information on deep learning research. It has launched an online space with three demos for image editing, styling, as well as photorealistic image synthesis. 
Computing

Give your discs some extra life by watching DVDs and Blu-rays on Windows 10

Popped a disc into your Windows machine but feel lost without Media Center? You're not alone. But don't fret, with just a few tips you can learn how to watch DVDs and Blu-rays for free in Windows 10 in no time.
Computing

Protecting your PDF with a password isn't difficult. Just follow these steps

If you need to learn how to password protect a PDF, you have come to the right place. This guide will walk you through the process of protecting your documents step-by-step, whether you're running a MacOS or Windows machine.
Emerging Tech

Gorgeous image of the Cosmic Bat nebula leaves us starry-eyed

The "Cosmic Bat" nebula has been captured in beautiful detail by the European Southern Observatory. Formally known as NGC 1788, the nebula is two thousand light-years away in a dark corner of the Orion constellation.
Emerging Tech

Super telescope captures supermassive black holes forming billions of years ago

The Subaru Telescope in Hawaii has captured evidence of supermassive black holes forming in the ancient universe. Astronomers discovered 83 quasars powered by supermassive black holes from billions of years ago.
Emerging Tech

Awesome Tech You Can’t Buy Yet: Write music with your voice, make homemade cheese

Check out our roundup of the best new crowdfunding projects and product announcements that hit the web this week. You may not be able to buy this stuff yet, but it sure is fun to gawk!
Emerging Tech

Mind-bending model shows Venus isn’t our nearest neighbor — it’s Mercury

Every textbook and table on the internet agrees -- the closest planet to Earth is Venus. But a new mathematical model shows that this is wrong. In fact, the planet closest to us on average is Mercury.
Emerging Tech

Desk lamps take on a new task by converting their light to power

What if we could charge devices using light from indoor sources like desk lamps? A group of scientists working on a technology called organic photovoltaics (OPVs) aim to do just that.
Emerging Tech

Body surrogate robot helps people with motor impairments care for themselves

A team from Georgia Tech has come up with an assistant robot to help people who have severe motor impairments to perform tasks like shaving, brushing their hair, or drinking water.
Emerging Tech

New Hubble image displays dazzling Messier 28 globular cluster

Messier 28 is a group of stars in the constellation of Sagittarius, located 18,000 light-years from our planet. Thousands of stars are packed tightly together in this sparkling image.
Emerging Tech

Cosmic dust bunnies: Scientists find unexpected ring around Mercury

A pair of scientists searching for a dust-free region near the Sun have made an unexpected discovery: a vast cosmic dust ring millions of miles wide around the tiny planet Mercury.
Emerging Tech

Take a dip in the Lagoon Nebula in first image from SPECULOOS instrument

The European Southern Observatory has released the first image collected by their new SPECULOOS instrument, and it's a stunning portrait of the Lagoon Nebula, a swirling cloud of dust and gas where new stars are born.
Emerging Tech

Robot assistants from Toyota and Panasonic gear up for the Tokyo Olympics

Japan plans to use the 2020 Olympics to showcase a range of its advanced technologies. Toyota and Panasonic are already getting in on the act, recently unveiling several robotic designs that they intend to deploy at the event.