Posted on 09/30/2021 7:50:43 PM PDT by DUMBGRUNT
Today, Intel introduced Loihi 2, its second-generation neuromorphic research chip, and Lava, an open-source software framework for developing neuro-inspired applications. Their introduction signals Intel’s ongoing progress in advancing neuromorphic technology.
Why It Matters: Neuromorphic computing, which draws insights from neuroscience to create chips that function more like the biological brain, aspires to deliver orders of magnitude improvements in energy efficiency, speed of computation and efficiency of learning across a range of edge applications: from vision, voice and gesture recognition to search retrieval, robotics, and constrained optimization problems.
Novel neural networks trainable by deep learning: Fully programmable neuron models and generalized spike messaging in Loihi 2 open the door to a wide range of new neural network models that can be trained in deep learning. Early evaluations suggest reductions of over 60 times fewer ops per inference on Loihi 2 compared to standard deep networks running on the original Loihi without loss in accuracy3.
(Excerpt) Read more at finance.yahoo.com ...
More details at the NON-LINKABLE ars Technica
Also, see Brains Behind the Brains: Mike Davies and Neuromorphic Computing at Intel Labs | Intel
This will not end well...calculators have it so most youth can’t give change from a dollar . Now they won’t even have to think?
This will not end well...calculators have it so most youth can’t give change from a dollar . Now they won’t even have to think?
Sorry for the double.
What could possibly go wrong?
—”This will not end well...calculators have it so most youth can’t give change from a dollar “
With biden inflation, fractions of a dollar will be near worthless...The labor cost of calculating change will exceed the value of the change...
And at the same time there will be a huge need for programmers dealing with:
“Put in terms of an actual neuron, part of the execution unit on the chip acts as a dendrite, processing incoming signals from the communication network based in part on the weight derived from past behavior. A mathematical formula was then used to determine when activity had crossed a critical threshold and to trigger spikes of its own when it does. The “axon” of the execution unit then looks up which other execution units it communicates with, and it sends a spike to each.”
You have the”Hello World” thing down, now get to work...
A million neuron-like switches per chip.
On average 86 billion neurons in a human brain - about 100,000 of these chips.
But the human cortex, where the higher thinking resides, is more like 10,000 to 20,000 of these chips.
Specialized parts of the human brain, that enable functions like hearing or seeing, can be much smaller. A human eye, fo example, has about 125 million neuron-like cells - about 100 of these chips.
Sub-human levels of function are achieved in nature, with many fewer neurons. A whole mouse brain for example, with all its ability to see, hear, smell, move and more; has the neuronal equivalent of only about 70 of these chips.
The software will take a while to work out, but this hardware puts us in range of the intelligence of living creatures. Better hardware is just a few more years away.
Robots are going to climb the evolutionary scale (interns of ability) quickly, from insect to mouse, to monkey, to human, to 10x human.
They can’t write either.
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.