Most Popular
1500 questions
10
votes
4 answers
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 particular use without the ability to change its…
kenorb
- 10,483
- 3
- 44
- 94
10
votes
2 answers
What is the double sample problem in reinforcement learning?
According to the SBEED: Convergent Reinforcement Learning with
Nonlinear Function Approximation for convergent reinforcement learning, the Smoothed Bellman operator is a way to dodge the double sample problem? Can someone explain to me what the…
Dhanush Giriyan
- 345
- 2
- 11
10
votes
1 answer
What is "early stopping" in machine learning?
What is early stopping in machine learning and, in general, artificial intelligence? What are the advantages of using this method? How does it help exactly?
I'd be interested in perspectives and links to recent research.
kenorb
- 10,483
- 3
- 44
- 94
10
votes
4 answers
What is the benefit of using identity mapping layers in deep neural networks like ResNet?
As I understand, ResNet has some identity mapping layers, whose task is to create the output as the same as the input of the layer. The ResNet solved the problem of accuracy degrading. But what is the benefit of adding identity mapping layers in…
Ali Abdari
- 121
- 1
- 7
10
votes
2 answers
How do evolutionary algorithms have advantages over the conventional backpropagation methods?
How does employing evolutionary algorithms to design and train artificial neural networks have advantages over using the conventional backpropagation algorithms?
kenorb
- 10,483
- 3
- 44
- 94
10
votes
2 answers
Can autoencoders be used for supervised learning?
Can autoencoders be used for supervised learning without adding an output layer? Can we simply feed it with a concatenated input-output vector for training, and reconstruct the output part from the input part when doing inference? The output part…
rcpinto
- 2,119
- 1
- 16
- 31
10
votes
1 answer
Can supervised learning be recast as reinforcement learning problem?
Let's assume that there is a sequence of pairs $(x_i, y_i), (x_{i+1}, y_{i+1}), \dots$ of observations and corresponding labels. Let's also assume that the $x$ is considered as independent variable and $y$ is considered as the variable that depends…
TomR
- 843
- 5
- 16
10
votes
2 answers
When should I use 3D convolutions?
I am new to convolutional neural networks, and I am learning 3D convolution. What I could understand is that 2D convolution gives us relationships between low-level features in the X-Y dimension, while the 3D convolution helps detect low-level…
Shobhit Verma
- 161
- 1
- 7
10
votes
1 answer
How can the emotional quotient of an AI program be measured?
Can an AI program have an EQ (emotional intelligence or emotional quotient)?
In other words, can the EQ of an AI program be measured?
If EQ is more problematic to measure than IQ (at least with a standard applicable to both humans and AI programs),…
1010101 Lifestyle
- 203
- 1
- 4
10
votes
3 answers
Are there any textual CAPTCHA challenges which can fool AI, but not human?
Are there any modern techniques of generating textual CAPTCHA (so person needs to type the right text) challenges which can easily fool AI with some visual obfuscation methods, but at the same time human can solve them without any struggle?
For…
kenorb
- 10,483
- 3
- 44
- 94
10
votes
3 answers
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 understand that this may be a bit of speculation and it's…
kenorb
- 10,483
- 3
- 44
- 94
10
votes
2 answers
Is neural networks training done one-by-one?
I'm trying to learn neural networks by watching this series of videos and implementing a simple neural network in Python.
Here's one of the things I'm wondering about: I'm training the neural network on sample data, and I've got 1,000 samples. The…
Ram Rachum
- 261
- 1
- 9
10
votes
1 answer
A mathematical explanation of Attention Mechanism
I am trying to understand why attention models are different than just using neural networks. Essentially the optimization of weights or using gates for protecting and controlling cell state (in recurrent networks), should eventually lead to the…
PixelPioneer
- 203
- 2
- 5
10
votes
1 answer
How to deal with a small amount of labeled samples?
I'm trying to develop skills to deal with very small amounts of labeled samples (250 labeled/20000 total, 200 features) by practicing on Kaggle "Don't Overfit" dataset (Traget_Practice have provided all 20,000 Targets). I've read a ton of papers and…
FirePower
- 201
- 1
- 3
10
votes
1 answer
Why don't people use nonlinear activation functions after projecting the query key value in attention?
Why don't people use nonlinear activation functions after projecting the query key value in attention?
It seems like doing this would lead to much-needed nonlinearity, otherwise, we're just doing linear transformations.
This observation applies to…
user3180
- 608
- 4
- 14