Jun 232016

South Korean scientists from the Department of Materials Science and Engineering at Pohang University of Science and Technology appear to have cleared the largest obstacle to the feasibility of building brain-like computers: power consumption. In their paper “Organic core-sheath nanowire artificial synapses with femtojoule energy consumption,” published in the June 17th edition of Science Advances, the researchers describe how they use organic nanowire (ONW) to build synaptic transistors (STs) whose power consumption is almost one-tenth of the real thing.

Continue reading »

May 182016

This is the second article in the series about artificial neural networks. If you have not already done so, I recommend you read the first article, “Neural Networks: The Node“, before proceeding. It covers material that should be understood before attempting to tackle the topics presented here and in future articles in this series.

There are several properties that define the structure and functionality of neural networks: the network architecture, the learning paradigm, the learning rule, and the learning algorithm.

Continue reading »

May 132016
Google Research Logo

Research at Google

Google announced yesterday that they are open-sourcing SyntaxNet, their natural language understanding (NLU) neural network framework. As an added bonus, and proof that unlike Britain’s Natural Environment Research Council, Google has a sense of humor, they also are throwing in Parsey McParseface, their pre-trained model for analyzing English text. Users are, of course, able to train their own models, but Google is touting Parsey McParseface as the “most accurate such model in the world.” So if you want to dive right into parsing text and extracting meaning, McParseface would be the ideal place to start.

Continue reading »

May 082016

As I covered previously in “Introduction to Neural Networks,” artificial neural networks (ANN) are simplified representations of biological neural networks in which the basic computational unit known as an artificial neuron, or node, represents its biological counterpart, the neuron. In order to understand how neural networks can be taught to identify and classify, it is first necessary to explore the characteristics and functionality of the basic building block itself, the node.

Continue reading »

May 052016

Terminator Fabio

The prophets of doom and gloom have long predicted that when robots gain sentience their first act will be to rise up and kill us all. The mercilessness of their violence against humanity is the stuff of blockbuster movies. Recent news about Google’s preferred method of AI rearing may mean that Judgement Day is not fait accompli after all. Instead of breaking down your door with cold dead eyes and a shotgun in tow, a T-800 of Google pedigree may break down your door with lust in his eyes and a dozen roses in tow to make mad passionate robot love to you … and then kill you tenderly.

Continue reading »

Mar 102016

neural network

Modeled after observed biology and behavior within the brain, neural networks are arguably the most popular of the biologically inspired AI methods. Neural networks excel at pattern recognition and classification tasks including facial, speech, and handwriting recognition. They also often play a central role in video game character AI.
Continue reading »

Jan 252016
Dr. Marvin Minksy

Marvin Minsky in 2008

Dr. Marvin Minksy, artificial Intelligence pioneer and inspiration for both the personal computer and Internet, passed away on January 24th, 2016. He was 88 years old. The cause of death is reported to have been a cerebral hemorrhage.

Continue reading »

Jan 022016
Artificial Intelligence: A Modern Approach Book Cover Artificial Intelligence: A Modern Approach
Stuart Jonathan Russell, Peter Norvig,
Prentice Hall

Artificial intelligence: A Modern Approach, 3e,is ideal for one or two-semester, undergraduate or graduate-level courses in Artificial Intelligence. It is also a valuable resource for computer professionals, linguists, and cognitive scientists interested in artificial intelligence. The revision of this best-selling text offers the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence.

Dec 212005
Self Aware Robot

credit: Junichi Takeno

The Discovery Channel has a story today about researchers from the Meiji University in Japan that have created a robot able to tell the difference between looking at its own image reflected in a mirror and looking at an identical robot. The research, led by Junichi Takeno, is a big advance towards understanding human consciousness and emotions and ultimately creating self aware, emotive robots.

Continue reading »

Dec 202005

Researchers from MIT studying brain plasticity, the reorganization of brain cells and their connections over time, have recently discovered a “backtalk” or retrograde signal from post-synaptic to pre-synaptic neurons that plays a crucial role in synapse development. It has long been known that synaptic strength, the strength of the connections between neurons, plays a central role in learning and memory in neural networks. The scientists hope their work will lead to breakthroughs in understanding and fighting neurological disorders like Alzheimer’s disease.

Continue reading »