What happens when you have Deep Learning begin to generate your designs? The commons misconception would be that a machine's design would look'mechanical' or'logical'. However, what we seem to be finding is that they look very organic, in fact they look organic or like an alien biology. Take a look at some of these fascinating designs. A Lightweight bike stem generated by an algorithm. Many of these designs come from Autodesk's DreamCatcher research.

Douglas Hofstader in his book "I am a Strange Loop" coined this idea: Where he describes this self-referential mechanism as what describes the unique property of minds. The strange loop is a cyclic system that traverses several layers in a hierarchy. By moving through this cycle one finds oneself where one originally started. Coincidentally enough, this'strange loop' is in fact is the fundamental reason for what Yann LeCun describes as "the coolest idea in machine learning in the last twenty years." Loops are not typical in Deep Learning systems.

I recently attended a presentation on TensorFlow. Towards the end someone asked the speaker, "what is the difference between deep learning and machine learning and why should I care?" The speaker replied with a rambling discussion of function generalization, overfitting, regularization … and the audience was even more confused. The answer to "why should I care" is actually quite straightforward. I created this diagram based on Andrew Ng's amazing AI talk.

NVIDIA has reported Q1 revenue of $1.94 billion, buoyed by record datacenter sales of $409 million. The datacenter business has been growing by leaps and bounds for the graphics chipmaker, thanks largely to the rapidly expanding market for high GPUs in deep learning. Revenue for the first quarter (Q1 FY18) beat analyst estimates and represents a 48 percent increase from last year at this time. Even more encouraging was net income, which amounted to $507 million for the quarter. That's more than twice that reported for the first quarter in 2016.

Apple has been pitching the Watch with ResearchKit to doctors and scientists as a serious health tool. Cardiogram initiated the research last year to figure out whether it could detect the signs of a stroke, a quarter of which are caused by irregular heartbeats. The study drew 6,158 Apple Watch users via the Cardiogram app -- most had normal EKG readings, but 200 had an existing AF condition that made their hearts beat erratically. Engineers used those subjects to train a deep learning system to discern patients with arrhythmia versus those with normal heartbeats. They then tested the system on 51 patients scheduled for a procedure to restore normal heart rhythms.

TensorFlow is a framework created by Google for creating Deep Learning models. Deep Learning is a category of machine learning models that use multi-layer neural networks. The idea of deep learning has been around since 1943 when neurophysiologist Warren McCulloch and mathematician Walter Pitts wrote a paper on how neurons might work and they modeled a simple neural network using electrical circuits. Many, many developments have occurred since then. These highly accurate mathematical models are extremely computationally expensive.

Deep learning and artificial intelligence are on their way to bringing about a sea change in how we use computers in medicine. Neural networks have the power to work toward solutions using approaches they devise on their own -- and it gives them incredible problem-solving capabilities. You can't exactly plug more RAM into a human brain (yet), but you can combine a supercomputer cluster with neural networks that do diagnostic image processing. This mighty partnership gives the ability to apply the collective wisdom and insight of doctors and scientists worldwide to the collective processing power of every core in the cluster.

Thanks to great experimental work by several research groups studying the behavior of Stochastic Gradient Descent (SGD), we are collectively gaining a much clearer understanding as to what happens in the neighborhood of training convergence. The story begins with the best paper award winner for ICLR 2017, "Rethinking Generalization". This paper I first discussed several months ago in a blog post "Rethinking Generalization in Deep Learning". One interesting observation in that paper is the role of SGD. Indeed, in neural networks, we almost always choose our model as the output of running stochastic gradient descent.

A link has been sent to your friend's email address.

Research into artificial intelligence is going gangbusters, and the frenetic pace won't let up for about five years -- after which the industry will concentrate around a handful of core technologies and leaders, the head of Intel's new AI division predicts. Intel is keen to be among them. In March, it formed an Artificial Intelligence Products Group headed by Naveen Rao. He previously was CEO of Nervana Systems, a deep-learning startup Intel acquired in 2016. Rao sees the industry moving at breakneck speed.