As artificial intelligence becomes more sophisticated, much of the public attention has focused on how successfully these technologies can compete against humans at chess and other strategy games. A philosopher from the University of Houston has taken a different approach, deconstructing the complex neural networks used in machine learning to shed light on how humans process abstract learning.
“As we rely more and more on these systems, it is important to know how they work and why,” said Cameron Buckner, assistant professor of philosophy and author of a paper exploring the topic published in the journal Synthese. Better understanding how the systems work, in turn, led him to insights into the nature of human learning.
Philosophers have debated the origins of human knowledge since the days of Plato – is it innate, based on logic, or does knowledge come from sensory experience in the world?
Deep Convolutional Neural Networks, or DCNNs, suggest human knowledge stems from experience, a school of thought known as empiricism, Buckner concluded. These neural networks – multi-layered artificial neural networks, with nodes replicating how neurons process and pass along information in the brain – demonstrate how abstract knowledge is acquired, he said, making the networks a useful tool for fields including neuroscience and psychology.
In the paper, Buckner notes that the success of these networks at complex tasks involving perception and discrimination has at times outpaced the ability of scientists to understand how they work.
While some scientists who build neural network systems have referenced the thinking of British philosopher John Locke and other influential theorists, their focus has been on results rather than understanding how the networks intersect with traditional philosophical accounts of human cognition. Buckner set out to fill that void, considering the use of AI for abstract reasoning, ranging from strategy games to visual recognition of chairs, artwork and animals, tasks that are surprisingly complex considering the many potential variations in vantage point, color, style and other detail.
“Computer vision and machine learning researchers have recently noted that triangle, chair, cat, and other everyday categories are so dif?cult to recognize because they can be encountered in a variety of different poses or orientations that are not mutually similar in terms of their low-level perceptual properties,” Buckner wrote. “… a chair seen from the front does not look much like the same chair seen from behind or above; we must somehow unify all these diverse perspectives to build a reliable chair-detector.”
To overcome the challenges, the systems have to control for so-called nuisance variation, or the range of differences that commonly affect a system’s ability to identify objects, sounds and other tasks – size and position, for example, or pitch and tone. The ability to account for and digest that diversity of possibilities is a hallmark of abstract reasoning.
The DCNNs have also answered another lingering question about abstract reasoning, Buckner said. Empiricists from Aristotle to Locke have appealed to a faculty of abstraction to complete their explanations of how the mind works, but until now, there hasn’t been a good explanation for how that works. “For the first time, DCNNs help us to understand how this faculty actually works,” Buckner said.
He began his academic career in computer science, studying logic-based approaches to artificial intelligence. The stark differences between early AI and the ways in which animals and humans actually solve problems prompted his shift to philosophy.
Less than a decade ago, he said, scientists believed advances in machine learning would stop short of the ability to produce abstract knowledge. Now that machines are beating humans at strategic games, driverless cars are being tested around the world and facial recognition systems are deployed everywhere from cell phones to airports, finding answers has become more urgent.
“These systems succeed where others failed,” he said, “because they can acquire the kind of subtle, abstract, intuitive knowledge of the world that comes automatically to humans but has until now proven impossible to program into computers.”
The Latest on: Deep Convolutional Neural Networks
via Google News
The Latest on: Deep Convolutional Neural Networks
- Artificial Neural Network Roundup: How ANNs Are Changing the Way We Research (and Engineer)on October 4, 2019 at 4:16 pm
Machine learning scientist David John Gagne from the National Center for Atmospheric Research (NCAR) used CNNs to train a deep learning model by showing the model large amounts of storm data. Gagne’s ...
- Aerial-trained deep learning networks for surveying cetaceans from satellite imageryon October 3, 2019 at 2:52 pm
Here we present a semi-automated pipeline for whale detection from very high-resolution (sub-meter) satellite imagery that makes use of a convolutional neural network (CNN). We trained ResNet, and ...
- Why build your own cancer-sniffing neural network when this 1.3 exaflop supercomputer can do if for you?on September 30, 2019 at 10:27 pm
The world’s fastest deep learning supercomputer is being used to develop algorithms that can ... and could zip through 7,033 patches per second. For comparison, a hand designed convolutional neural ...
- Yann LeCun: Deep Learning, Convolutional Neural Networks, and Self-Supervised Learningon August 31, 2019 at 9:00 am
He is a professor at New York University, a Vice President & Chief AI Scientist at Facebook, co-recipient of the Turing Award for his work on deep learning. He is probably best known as the founder of ...
- Utilizing a Convolutional Neural Network To Predict HIV-1 Tat Biological Functionson August 28, 2019 at 6:00 am
This study proposes to utilize deep learning techniques to perform analysis inference ... consistent with annotations of the Gene Ontology (GO) Consortium, a convolutional neural network (CNN) was ...
- Fault detection and classification with feature representation based on deep residual convolutional neural networkon August 15, 2019 at 5:00 pm
Abstract This paper proposes a novel fault detection and classification method via deep residual convolutional neural network (DRCNN). The DRCNN captures the deep process features represented by ...
- Is Deep Learning Just Neural Networks on Steroids?on July 3, 2019 at 2:15 pm
Takeaway: Is “deep learning” just another name for advanced neural ... (reproduced from Adit Deshpande’s “A Beginner’s Guide To Understanding Convolutional Neural Networks”). By adding more ...
- Convolutional Neural Network Deep Learning Techniques for Crowd Countingon April 7, 2019 at 5:00 pm
Deep learning techniques like Convolutional Neural Networks (CNNs) are a better choice for crowd-counting use cases, compared to traditional detection or regression based models. Ganes Kesari, ...
- Certifying attack resistance of convolutional neural networkson January 31, 2019 at 7:52 am
Current deep neural network models are known to be vulnerable ... provides a general and efficient framework for certifying the level of adversarial robustness of convolutional neural networks to ...
via Bing News