# Tag Info

10

H+ magazine wrote an estimate in 2009 that seems broadly comparable to other things I've seen; they think the human brain is approximately 37 petaflops. A supercomputer larger than that 37 petaflop estimate exists today. But emulation is hard. See this SO question about hardware emulation or this article on emulating the SNES, in which they require 140 ...

7

Quick Answer When Intel acquired Nirvana, they indicated their belief that analog VLSI has its place in the neuromorphic chips of the near future1, 2, 3. Whether it was because of the ability to more easily exploit the natural quantum noise in analog circuits is not yet public. It is more likely because of the number and complexity of parallel activation ...

6

I think, there are various reasons. First of all: Flexibility. With modern CPUs and GPUs you can construct pretty much every AI model you want and in every size and complexity you want. How can you be sure that the model you are currently using is still suitable in a few years? Maybe there will be a major breakthrough in NNs in the next few years? Maybe some ...

6

The human brain contains about 100 billion neurons ($10^{11}$) and about a hundred trillion synapses ($10^{14}$). Each neuron can fire about 100 times a second. If we model the brain as a simple neural network, then it would be equivalent to a machine that requires 1016 calculations per second and 1013 bits of memory. From Wikipedia Kurzweil introduces the ...

6

Vernor Vinge said that if we can scan a human brain and then simulate it: We can run it at 1000 times the speed. The brain will be able to do 1000 years of thinking in 1 year ect. At this stage in history we have the computer power. The trouble lies in cutting a brain up and scanning the 100 billion neurons and 12 million kilometres of axons and 100000 ...

5

Second question first: Data is stored in an ANN in the form of weights in the adjacency matrix between neurons. During training, these weights are updated by a learning algorithm (such as backpropagation). First question: according to award-winning neuroscientist Tim Bliss: “It’s been accepted really since the turn of the 20th century, since the time of ...

5

Tensor operations The major work in most ML applications is simply a set of (very large) tensor operations e.g. matrix multiplication. You can do that easily in an ASIC, and all the other algorithms can just run on top of that.

4

It looks like you really have two questions here. I'll try to answer the first one, and you should think about making a separate question for the second. There is research into using simulated models of biologically realistic neurons. While there are large projects like the Human Brain Project aimed at simulating human brains, there is also a lot of lower-...

4

State of Rosehip Research The Rosehip neuron is an important discovery, with vast implications to AI and its relationship to the dominant intelligence on earth for at least the last 50,000 years. The paper that has spawned other articles is Transcriptomic and morphophysiological evidence for a specialized human cortical GABAergic cell type, Buldog et. al.,...

3

It is true that the current Machine learning is based on treating neurons as a component in the whole complexity , mesh of neurons. The focus is more on the architecture rather than understanding or imitating the basic block of it more clearly , i.e. the neurons. Anirban Bandhopadhyay is a biologist and Neurologist who has studied how the harmony changes ...

3

Digital Instrumentation of the Analog Cells One of the key challenges in analog artificial networks is that network instrumentation would be most practical if digital. Any VLSI implementation of analog perceptrons, convolutions, or spiking networks will likely need to have digital components in a hybrid arrangement for several functions. Health indicators ...

3

Principles of Computational Modelling in Neuroscience by David Sterratt, Bruce Graham, Andrew Gillies and David Willshaw discuss it in Chapter 7 (The synapse) and also in Chapter 8 (Simplified models of neurons). Especially in chapter 8, they discuss how to add excitatory or inhibitory synapses to integrate and fire neuron. There are various ways to add ...

3

Neuromorphic engineering offers various of ways of reproducing the brain’s processing ability. The recent technology can include IBM's multi-artificial-neuron computer, the world's first artificial nanoscale stochastic phase-change neuronsarticle. Check the: Stochastic phase-change neurons study. Other can include Neurogrid, built by Brains in Silicon at ...

3

I think the algorithm has changed minimally, but the necessary hardware has been trimmed to the bone. The number of gate transitions are reduced (perhaps float ops and precision too), as are the number of data move operations, thus saving both power and runtime. Google suggests their TPU achieves a 10X cost saving to get the same work done. https://...

2

Not just how much, but what kind of processing power : there're specially-crafted dedicated chips, and it has a practical applications, so it's not a lab-only project

2

In biology, when the presynaptic releases a neurotransmitter (a positive amount of them, obviously), this neurotransmitter reaches the postsynaptic vesicles causing an excitatory (depolarization) or inhibitory (hyperpolarization) effect, depending on the kind of postsynaptic vesicle in next cell dendrites. If the total amount of depolarization (all dendrites)...

2

One can also approach the question from the information theory aspect: There are two trade/offs to choose from: Analog information that may represent information in a more precise/specific way, but limited in quantity. Digital information that doesn't fully represent the real world, but may contain unlimited amount of information within a few bits. A good ...

2

I believe that most people have pretty much answered the question diligently in a really informative way. I would just like to say that we use digital circuits commonly because that is the existing technology and that definitely analog circuits seem really promising. However, at this moment, this idea is not very well-developed despite the amount of ...

2

No. The reasons include but are not limited to: lack of understanding of how the brain works current ANNs are mostly good at pattern recognition and generative tasks, but lack the capacity to create abstractions on their own we can't match the size/number of artificial neurons to the number of biological neurons even with a much smaller ANN size, ...

1

The most popular theoretical framework in use currently, in the neuromorphic (brain-inspired) computing community is the Neural Engineering Framework (NEF). Neural Engineering by Chris Eliasmith and Charles Anderson explains the framework comprehensively. As a follow up to that, How to Build a Brain by Chris Eliasmith describes the more recent and more high-...

1

There is a category of neural networks that more closely attempt to mimic biological neural networks by incorporating also time (i.e. not all neurons fire at the same time). They are called spiking neural networks (SNNs) and their name comes from the fact that they use spiking neurons (i.e. neurons that fire discrete signals and affect other neurons at ...

1

Assumption In this answer it is assumed that with "neurochips" you mean chips made (using neuromorphic engineering) for neuromphic computing. Related example From what I currently understand from this article neuromorphic chips, in particular the TrueNorth chip, are being used (or emulated) for embedded systems related signals processing. Doubt The ...

1

The Degree to Which Inhibition is in Common Use What could loosely be considered inhibitory effect occurs in MLPs (multilayer perceptrons) as they are normally designed and implemented already. The gradient descent scheme implemented within a larger back propagation algorithm can produce a parameter adjustment delta that is either positive or negative. A ...

1

It's been done (essentially). This guy at the following link has used a series of FPGAs to emulate hundreds of 8080s, using them to train a neural network to play Gameboy games. https://towardsdatascience.com/a-gameboy-supercomputer-33a6955a79a4 IBM's True North being used in Darpa's SyNAPSE program is also very close to what you suggest. https://en....

Only top voted, non community-wiki answers of a minimum length are eligible