Month: July 2018

New Algorithm that outperforms Deep Learning

Leave a comment

Deep Learning is blooming and with it, all kinds of unthought applications have been sprung to life. Every tech company is trying to implement a form of AI in their businesses in some way or the other. Neural networks, after all, have begun to outperform humans in tasks such as object and face recognition and in games such as chess, Go, and various arcade video games. And as we all know, Deep Learning is a manifestation of the human brain and has tremendous potential.

However, An entirely different type of computing has the potential to be significantly more powerful than neural networks and deep learning. This technique is based on the process that created the human brain—evolution. In other words, a sequence of iterative change and selection that produced the most complex and capable machines known to humankind—the eye, the wing, the brain, and so on. The power of evolution is a wonder to behold.

atari-evolutionary-comp.jpg

Evolution

 

Dennis Wilson and a few colleagues at the University of Toulouse in France have shown how evolutionary computing can match the performance of deep-learning machines at the emblematic task that first powered them to fame in 2013—the ability to outperform humans at arcade video games such as Pong, Breakout, and Space Invaders. The work suggests that evolutionary computing should be feted just as widely as its deep-learning-based relations.
Evolutionary computing is completely unlike Deep Learning. The conventional way to create code is to write it from first principles with a specific goal in mind. Evolutionary computing uses a different approach. It starts with code generated entirely at random. And not just one version of it, but lots of versions, sometimes hundreds of thousands of randomly assembled pieces of code, and each of these codes have been tested to check whether the end goal is achieved. As a result, a lot of code is generated. But just by chance, some pieces of code are a little better than others. These pieces are then reproduced in a new generation of code, which includes more copies of the better codes.

However, the next generation cannot be an identical copy of the first. Instead, it must change in some way. These changes can involve switching two terms in the code—a kind of point mutation. Or they can involve two codes that are cut in half and the halves exchanged—like sexual recombination.

Each of the new generations is then tested to see how well it works. The best pieces of code are preferentially reproduced in another generation, and so on. In this way, the code evolves. Over time, it becomes better, and after many generations, if conditions are right, it can become better than any human coder can design.

 

via: MitTechReview, Medium

Smelling illness in human breath using AI

Leave a comment

Researchers from Loughborough University, Western General Hospital, the University of Edinburgh, and the Edinburgh Cancer Centre in the United Kingdom, recently developed a deep learning-based method that can analyze compounds in the human breath and detect illnesses, including cancer, with better than-human average performance.

The sense of smell is used by animals and even plants to identify hundreds of different substances that float in the air. But compared to that of other animals, the human sense of smell is far less developed and certainly not used to carry out daily activities. For this reason, humans aren’t particularly aware of the richness of information that can be transmitted through the air and can be perceived by a highly sensitive olfactory system. AI may be about to change that.

Using NVIDIA Tesla GPUs and the cuDNN-accelerated Keras, and TensorFlow deep learning frameworks, the team trained their neural network on data from participants with different types of cancer receiving radiotherapy, said researcher Angelika Skarysz, a Ph.D. research student at Loughborough University. To increase the neural network’s efficiency, the team increased the original training data by using data augmentation. The convolutional neural network was augmented 100 times, the team said.

AI_Illness_Detection_Arch.png

 

“A team of doctors, nurses, radiographers and medical physicists at the Edinburgh Cancer Centre collected breath samples from participants undergoing cancer treatment. The samples were then analyzed by two teams of chemists and computer scientists. Once a number of compounds were identified manually by the chemists, fast computers were given the data to train deep learning networks. The computation was accelerated by special devices, called GPUs, that can process multiple different pieces of information at the same time. The deep learning networks learned more and more from each breath sample until they could recognize specific patterns that revealed specific compounds in the breath” as posted by Andrea Soltoggio on The Conversation.

3d-view-breathsampledata.png

3D view of a portion of breath sample data

“Computers equipped with this technology only take minutes to autonomously analyze a breath sample that previously took hours by a human expert,” Soltoggio said. AI is making the whole process cheaper – but above all, it is making it more reliable.

Link to the paper: ResearchGate

(Via: ResearchGate, The Conversation, NVidia)