Stories tagged AI

This video shows the evolution of coordinated behavior of simulated robot soccer players. In the simulation, each soccer player is controlled by a neural network. The neural networks are evolved using an evolutionary algorithm, so generation after generation the strategy improves.
The corresponding paper "Evolving neural network controllers for a team of self-organizing robots" is available at


Finding better ways for computers to see


Building biologically-inspired vision systems

Living organisms are very good at making sense out of what they see. Designing machines that can recognize objects when seen from an angle or at various distances is challenging. Facial or gesture recognition is becoming common in our computing devices.

Reverse engineering the visual cortex

In an attempt to improve upon current state of the art visual systems, scientists are attempting to reverse engineer biological visual systems.

Huge advances have been recently made in visualizing the structure of our visual cortex (hardware) but the inner workings of the neuronal systems (software) remain a mystery. Mimicking natural selection, scientists are testing thousands of software algorithms at a time.

Using processors from game playing computers

Using graphical processors from game playing computers (such as those found in the PlayStation 3 and high-end NVIDIA graphics cards), scientists have discovered better visual modeling systems.

"The best of these models, drawn from thousands of candidates, outperformed a variety of state-of-the-art vision systems across a range of object and face recognition tasks."

"GPUs are a real game-changer for scientific computing. We made a powerful parallel computing system from cheap, readily available off-the-shelf components, delivering over hundred-fold speed-ups relative to conventional methods,"

PLoS Computational Biology published research paper
Visual Neuroscience Group @ The Rowland Institute at Harvard


Reverse engineering the brain
Reverse engineering the brainCourtesy Thomas Schultz

Engineering computers that can think

Even simple brains, like those in a mouse, are amazing. A brain the size of a thimble that requires almost no energy, can navigate through mazes, survive in severe weather, or escape from a cat. Will we ever create a computer capable of such adaptable and creative "thinking"? One approach is to reverse engineer the brain of a mouse, rat, or cat.

Computer simulation achieves cat brain complexity

Dharmendra S. Modha is a team leader at IBM who is attempting to understand and build such a brain as cheaply as possible. Their latest achievement is a brain simulation with 1 billion spiking neurons and 10 trillion individual learning synapses.

Synapses are the key

Synapses are junctions between neurons and a key to how a brain learns. The strength of the chemical reactions within the synapses changes as the animal interacts with the environment These synaptic junctions are thought to encode our individual experience.

The problem with today's computers

Regular computer architecture has a separation between computation and memory.

“Surely there must be a less primitive way of making big changes in the store than by pushing vast numbers of words back and forth through the von Neumann bottleneck. Not only is this tube a literal bottleneck for the data traffic of a problem, but, more importantly, it is an intellectual bottleneck that has kept us tied to word-at-a-time thinking instead of encouraging us to think in terms of the larger conceptual units of the task at hand. Thus programming is basically planning and detailing the enormous traffic of words through the von Neumann bottleneck, and much of that traffic concerns not significant data itself, but where to find it.”

DARPA's SyNAPSE program

The goal of a DARPA program known as SyNAPSE (Systems of Neuromorphic Adaptive Plastic Scalable Electronics) is to create new electronics hardware and architecture that can understand, adapt and respond to a a changing environment.

What is cognitive computing?

Cognitive computing is the quest to engineer mind-like intelligent machines by reverse-engineering the computational function of the brain.

There is no definition or specification of the human mind. But, we understand it as a collection of processes of sensation, perception, action, cognition, emotion, and interaction. Yet, the mind seems to integrate sight, hearing, touch, taste, and smell effortlessly into a coherent whole, and to act in a context-dependent way in a changing, uncertain environment. The mind effortless creates categories of time, space, and object, and interrelationships between these.

Learn more about cognitive computing


Robots that "think for themselves"

Fly's eyes: Can the nerves, eyes, and brain function of a fly be modeled within a computer circuit?
Fly's eyes: Can the nerves, eyes, and brain function of a fly be modeled within a computer circuit?Courtesy NeilsPhotography
Engineers are trying to design machines that can "think for themselves" when on surveillance or search and rescue missions. Somehow the machines has to look at its environment and decide what to do.
Have you ever tried to catch a fly? They are pretty good at seeing your hand and knowing just how to escape your grasp.

If we can figure out how a fly can do it ...

Can we figure out how a fly is able see, and find food, and escape from our fly swatters? With today's super microscopes, I am sure that we can visualize and model every nerve connection, muscle fiber, and eye facet.

Computational biology

David O’Carroll, a computational neuroscientist who studies insect vision at Australia’s University of Adelaide has been studying the optical flight circuits of flies, measuring their cell-by-cell activity. In a paper published in Public Library of Science Computational Biology, O’Carroll and fellow University of Adelaide biologist Russell Brinkworth describe an

algorithm composed of a series of five equations through which data from cameras can be run. Each equation represents tricks used by fly circuits to handle changing levels of brightness, contrast and motion, and their parameters constantly shift in response to input.

The "fly brain" circuits are small and use only a fraction of a milliwatt

“It’s amazing work,” said Sean Humbert, who builds miniaturized, autonomous flying robots,

“For traditional navigational sensing, you need lots of payload to do the computation. But the payload on these robots is very small — a gram, a couple of Tic Tacs. You’re not going to stuff dual-core processors into a couple Tic Tacs.

Learn more - mathematical modeling of insect biology

Secret Math of Fly Eyes Could Overhaul Robot Vision Wired Science
Robust Models for Optic Flow Coding in Natural Scenes Inspired by Insect Biology Computational Biology

We have constructed a full model for motion processing in the insect visual pathway incorporating known or suspected elements in as much detail as possible. We have found that it is only once all elements are present that the system performs robustly, with reduction or removal of elements dramatically limiting performance. The implementation of this new algorithm could provide a very useful and robust velocity estimator for artificial navigation systems.


Computer mistaken for human

Elbot the chatbot: Click to chat with Elbot
Elbot the chatbot: Click to chat with ElbotCourtesy Artificial Solutions
Last week Elbot fooled three judges out of twelve into thinking it was a real human being. Elbot, an artificial intelligence program, has been developed over the last seven years by Artificial Solutions. Elbot is their most intelligent "chatbot" and has an enormous knowledge base. If you want to have a chat with Elbot, you can visit him at

Best yet performance yet by an AI

Elbot won this year's Loebner Prize which goes to chatbot software most able to converse like a human. Each year an annual prize of $3000 and a bronze medal is awarded to the most human-like computer (the Loebner 2008 Rules can be found by clicking here). Dr. Hugh Loebner pledged a Grand Prize of $100,000 and a Gold Medal for the first computer to fool 30% of the judges (Elbot fooled 25%).

Source: New Scientist Tech

A computer program called CyberLover mimics the conversation of an on-line dating service chat room. The program fools users into divulging personal information, which can lead to identity theft -- and heartbreak.


Our understanding of how things work increases every year. This increased understanding has led to ever improving technologies. When improved technology increases our ability to learn, the resulting accelleration of our intelligence approaches infinity.
Humans have an upper limit on the size and speed of their brains. Not so for machines. If machines can be programmed to learn, then machines can create a smarter machines. The smarter machine could then create an even smarter machine, etc. The result eventually leads to an intelligence that could undoubtedly solve all our problems. Global warming, disease, famine, and warfare could all be cured by such an "infinite" intelligence.

A Singularity Summit

These concepts and other mind boggling ideas were presented at the Singularity Summit at Stanford University last week. The first speaker was Ray Kurzweil, whos recent 672-page book, The Singularity Is Near : When Humans Transcend Biology explains a concept known as the "singularity".

If you aren’t familiar with the concept of singularity, here is the elevator pitch:

Sometime in the next few years or decades, humanity will become capable of surpassing the upper limit on intelligence that has held since the rise of the human species. We will become capable of technologically creating smarter-than-human intelligence, perhaps through enhancement of the human brain, direct links between computers and the brain, or Artificial Intelligence. This event is called the "Singularity" by analogy with the singularity at the center of a black hole - just as our current model of physics breaks down when it attempts to describe the center of a black hole, our model of the future breaks down once the future contains smarter-than-human minds. Since technology is the product of cognition, the Singularity is an effect that snowballs once it occurs - the first smart minds can create smarter minds, and smarter minds can produce still smarter minds. —Singularity Institute for Artificial Intelligence

Douglas Hofstader followed Kurzweil, offering his critique of the Singularity. Hostader, professor of Cognitive Science and Computer Science Adjunct Professor of History and Philosophy of Science, Philosophy, Comparative Literature, and Psychology at the University of Indiana and the author of Gödel, Escher, Bach: An Eternal Golden Braid, doesn't buy into the whole Singularity vision.

The purpose of life

I strongly recommend exploring this "Singularity" concept. I first came across it several years ago when I went to "Ask Jeeves" with my question "What is the purpose of life"? Jeeves recommended contributing to the "seed program" effort to create a "learning how to learn program" that would insure that when machines became super intelligent they would still take care of humans.

More Singualrity links: