Questions tagged [hardware]

For questions involving, but not exclusively about, hardware. (Please use the "hardware-evaluation" for questions exclusively about analysis of hardware components.)

Filter by
Sorted by
Tagged with
0 votes
0 answers
8 views

How to Implement decision tree on FPGA?

I have a large decision tree (depth 80, decision node ~25000 and leaf node ~25000) trained on sklearn decision tree classifier. I am thinking to implement it on an FPGA board. What would be the best ...
user avatar
  • 19
1 vote
0 answers
42 views

Difference between TPU and VPU

There are these two concepts of ASICs for the usage for neural networks. The one is called Tensor Processing Unit (TPU) and the other one is called a Vision Processing Unit (VPU). How do they differ ...
user avatar
  • 11
3 votes
1 answer
214 views

What exactly is an XPU?

I know about CPU, GPU and TPU. But, it is the first time for me to read about XPU from PyTorch documentation about MODULE. ...
user avatar
  • 2,977
1 vote
0 answers
24 views

How does optical computing work and deal with nonlinearity?

This article states that: One of the algorithms that photonics is very good at implementing is matrix multiplication But how are parameters stored and updated(in backpropagation)? One more ...
user avatar
6 votes
0 answers
100 views

How do neural network topologies affect GPU/TPU acceleration?

I was thinking about different neural network topologies for some applications. However, I am not sure how this would affect the efficiency of hardware acceleration using GPU/TPU/some other chip. If, ...
user avatar
1 vote
2 answers
610 views

How long it takes to train face recognition deep neural network? (rough estimation)

If I use a desktop PC with a GPU, how long it might take to train face recognition deep neural network on let's say dataset of 2.6 million images and 2600 identities? I guess it should depend on ...
user avatar
  • 113
1 vote
2 answers
4k views

Does fp32 & fp64 performance of GPU affect deep learning model training? [closed]

I am purchasing Titan RTX GPU. Everything seems fine with that except float32 & float64 performance which seems lower vis-a-vis some of its counter parts. I wanted to understand if single ...
user avatar
3 votes
1 answer
166 views

What are the aspects that most impact on the inference time for neural networks in embedded systems?

I work with neural networks for real-time image processing on embedded softwares and I tested different architectures (Googlenet, Mobilenet, Resnet, custom networks...) and different hardware ...
user avatar
  • 269
0 votes
2 answers
96 views

Tips for keeping the distribution of weights normal

I am working on a project where the Neural Network weights must be quantized on 8 or 16 bits for an embedded platform, thus I will lose some precision. Since our platform does not have floating point ...
user avatar
-1 votes
1 answer
54 views

Does software remain even when hardware is demolished?

For example, if I constructed a neural network and the computer running it where to be demolished, is the information/program of the neural network still an existent entity within or outside the ...
user avatar
5 votes
1 answer
111 views

Which artificial intelligence algorithms could use tensor specific hardware?

AI algorithms involving neural networks can use tensor specific hardware. Are there any other artificial intelligence algorithms that could benefit from many tensor calculations in parallel? Are ...
user avatar
2 votes
2 answers
178 views

Are artificial networks based on the perceptron design inherently limiting?

At the time when the basic building blocks of machine learning (the perceptron layer and the convolution kernel) were invented, the model of the neuron in the brain taught at the university level was ...
user avatar
2 votes
3 answers
142 views

Could a large number of interconnected tiny turing-complete computer chips be patterned across a wafer to simulate a programmable neural network?

The Intel 8080 had 4500 transistors and ran at 2-3.125 MHz. By comparison, the 18-core Xeon Haswell-E5 han 5,560,000,000 transistors and can run at 2 GHz. Would it be possible or prudent to simulate a ...
user avatar
3 votes
2 answers
266 views

What is the difference between a normal processor and a processor designed for AI?

What is the difference between a normal processor and a processor designed for AI?
user avatar
7 votes
1 answer
2k views

Who manufactures Google's Tensor Processing Units? [closed]

Does google manufacture TPUs? I know that google engineers are the ones responsible for the design, and that google is the one using them, but which company is responsible for the actual manufacturing ...
user avatar
7 votes
1 answer
1k views

Are more than 8 high performance Nvidia GPUs practical for deep learning applications? [closed]

I was prompted towards this question while trying to find server racks and motherboards which are specialized towards artificial intelligence. Naturally I went to the SuperMicro website. There the ...
user avatar
8 votes
1 answer
298 views

How powerful is the machine that beat the poker professional players recently?

How powerful is the machine that beat the poker professional players recently (DeepStack)?
user avatar
2 votes
1 answer
61 views

If we achieve sentience using mutable hardware, will it be possible to make a copy of that "brain" and its active state?

Hardware comes in two forms, basically: immutable, such as RAM, and mutable, such as FPGAs. In animals, neurological connections gain in strength by changing the physical structure of the brain. This ...
user avatar
10 votes
4 answers
785 views

Are we technically able to make, in hardware, arbitrarily large neural networks with current technology?

If neurons and synapses can be implemented using transistors, what prevents us from creating arbitrarily large neural networks using the same methods with which GPUs are made? In essence, we have ...
user avatar
10 votes
4 answers
4k views

How does using ASIC for the acceleration of AI work?

We can read on Wikipedia page that Google built a custom ASIC chip for machine learning and tailored for TensorFlow which helps to accelerate AI. Since ASIC chips are specially customized for one ...
user avatar
  • 10k
9 votes
3 answers
4k views

How powerful a computer is required to simulate the human brain?

How much processing power is needed to emulate the human brain? More specifically, the neural simulation, such as communication between the neurons and processing certain data in real-time. I ...
user avatar
  • 10k
5 votes
1 answer
210 views

Are there any microchips specifically designed to run ANNs?

I'm interested in hardware implementation of ANNs (artificial neural networks). Are there any popular existing technology implementations in form of microchips which are purpose designed to run ...
user avatar
  • 10k