Deep learning has created a resurgence of interest in neural networks and their application to everything from Internet search to self-driving cars. Results published in the scientific and technical literature show better-than-human accuracy on real-world tasks that include speech and facial recognition.
Fueled by modern massively parallel computing technology, it is now possible to train very complex multi-layer neural network architectures on large data sets to an acceptable degree of accuracy. This is referred to as deep-learning, as these multi-layer networks interpose many neuronal processing layers between the input data and the output results calculated by the neural network — hence the use of the word deep in the deep-learningcatchphrase. The resulting trained networks can be extremely valuable, as they have the ability to perform complex, real-world pattern recognition tasks very quickly on a variety of low-power devices including sensors, mobile phones, and FPGAs, as well as quickly and economically in the data center.
Generic applicability, high accuracy (sometimes better than human), and ability to be deployed nearly everywhere explains why scientists, technologists, entrepreneurs and companies are all scrambling to take advantage of deep-learning technology.
Machine learning went through a similar bandwagon stage in the 1980s where superlatives were lauded on the technology and futurists discussed how machine learning was going to change the world. The genesis of the 1980s machine- earning revolution was a seminal paper by Hopfield and Tank, “Neural Computation of Decisions in Optimization Problems,” which showed that good solutions to a wide class of combinatorial optimization problems could be found using networks of biology-inspired neurons. In particular, Hopfield and Tank demonstrated they could find good solutions to intractably large versions of the NP-Complete traveling salesman problem.
The advent of backpropagation by Rummelhart, Hinton and Williams allowed the adjustment of weights in a ‘neurone-like’ network so the network could be trained to solve a computational problem from example data. In particular, the ability of neural networks to adjust their weights to learn all the logic functions required to build a general purpose computer — including the non-linear XOR truth table — showed that artificial neural networks (ANNs) are computationally universal devices that can, in theory, be trained to solve any computable problem. I like to joke that machine learning made me one of the hardest working lazy men you would ever meet, as I was willing to work very hard to make the computer teach itself to solve a complex problem.
Nettalk, a beautiful example by Terry Sejnowski and Charles Rosenberg, showed that it was possible to teach a neural network to perform tasks at a human-level of complexity — specifically to read English text aloud. Even grade-school children immediately grasp the implications of machine learning through the NetTalk example, as people can literally hear the ANN learn to read aloud. Further, it is easy to show that the ANN had ‘learned’ a general solution to the problem of reading aloud, as it could correctly pronounce words that it had never seen before. I use NetTalk as a stellar example of how scientists can create simple and intuitively obvious examples to communicate their research to anyone.
The bandwagon faded for ANNs during the mid-1990s as overblown claims and a lull in the development of parallel computing exceeded both the patience of funding agencies and limited the size and complexity of the problems that could be addressed. Neural networks faded from the scientific limelight, while research continued to both expand and mature the technology. Still, examples such as Star Trek’s Commander Data preserved the popular perception of the potential of neural network technology.
The development of low-cost massively parallel devices like GPUs sparked a resurgence in the popularity of neural network research. Instead of spending $30M to purchase a 60 GF/s (billion flop/s) Connection Machine, modern researchers can now purchase a TF/s (trillion flop/s) capable GPU for around a hundred dollars. The parallel mapping pioneered by Farber on the Connection Machine at Los Alamos allows the computationally expensive training step to very efficiently map any SIMD architecture, be it a GPU or the vector architecture of an Intel Xeon or Intel Xeon Phi processor. Near-linear scalability in a distributed computing environment means that most computational clusters can achieve very efficient, near-peak performance during the training phase. For example, the 1980s mapping used on a Connection Machine was able to achieve over 13 PF/s (1015 flop/s) average sustained performance on the OakRidge National Laboratory Titan supercomputer. The ability to run efficiently on large numbers of either vector or GPU devices means that researchers can work with complex neural networks and large data sets to solve problems — sometimes as well or better than humans.
“The ability to run efficiently on large numbers of either vector or GPU devices means that researchers can work with complex neural networks and large data sets to solve problems — sometimes as well or better than humans.”
Convolutional neural networks (CNNs) are a form of ‘deep’ neural network architecture popularized by Yann LeCun and others in 1998. CNNs are behind many of the deep-learning successes that have been reported recently in image and speech recognition. Again inspired by biology, these neural networks find features in the data that permit correct classification or recognition of the training images without the help of a human. The lack of dependence on prior knowledge and human effort is considered a major advantage of CNNs over other approaches.
The Latest on: Deep Learning
via Google News
The Latest on: Deep Learning
- Learn AI and deep learning with this bundle, for a price you chooseon August 16, 2019 at 11:15 am
AI and deep learning are transforming the way we understand software, used across a broad range of industries to produce hardware like self-driving cars, personal assistant computers, and decision ...
- DeepCC: a novel deep learning-based framework for cancer molecular subtype classificationon August 16, 2019 at 10:57 am
Molecular subtyping of cancer is a critical step towards more individualized therapy and provides important biological insights into cancer heterogeneity. Although gene expression signature-based ...
- Squirrel AI Learning by Yixue Group Learning Won Best Paper & Best Student Paper Award at ACM KDD International Symposium on Deep Learning on Graphon August 16, 2019 at 2:41 am
ANCHORAGE, Alaska, Aug. 14, 2019 /PRNewswire/ -- The first international symposium on deep learning on graph: methods and applications (DLG 2019) was held in Anchorage, Alaska, the US on August 5 ...
- Towards perturbation prediction of biological networks using deep learningon August 16, 2019 at 2:10 am
The mapping of the physical interactions between biochemical entities enables quantitative analysis of dynamic biological living systems. While developing a precise dynamical model on biological ...
- Global Closed-circuit Television (CCTV) Camera Market 2019-2023| Introduction of Deep Learning Technology to Boost Growth| Technavioon August 15, 2019 at 9:47 am
Technavio has published a new market research report on the global closed-circuit television (CCTV) camera market from 2019-2023 (Graphic: Business Wire) The growing demand for IP-based CCTV cameras ...
- A day at the beach: Deep learning for a childon August 14, 2019 at 2:34 pm
The beach offers a wide open playscape where children are fuelled by curiosity. Whether at the beach or elsewhere outdoors, it helps to take a moment to see the world through the lens of a child ...
- Master data analytics and deep learning with this $35 Python certification bundleon August 13, 2019 at 10:02 am
Python is one of the easiest programming languages to learn, but mastering it allows you to build apps and games or even take advantage of neural networks for deep learning. But first, you’ll need to ...
- Global Deep Learning Market Outlook 2019-2025: Anticipating a CAGR of 42.3%on August 12, 2019 at 8:34 am
Dublin, Aug. 12, 2019 (GLOBE NEWSWIRE) -- The "Deep Learning - Market Analysis, Trends, and Forecasts" report has been added to ResearchAndMarkets.com's offering. Deep Learning market worldwide is ...
- Sightcorp deep learning method improves biometric face detection at challenging angleson August 9, 2019 at 8:57 am
Artificial intelligence software company Sightcorp has developed improved biometric facial detection capabilities for facial analysis and recognition software based on deep learning, rather than ...
- What Is Deep Learning?on August 8, 2019 at 7:25 am
Deep learning, an advanced artificial intelligence technique, has become increasingly popular in the past few years, thanks to abundant data and increased computing power. It's the main technology ...
via Bing News