29
votes
Accepted
What is sample efficiency, and how can importance sampling be used to achieve it?
An algorithm is sample efficient if it can get the most out of every sample. Imagine yourself playing PONG for the first time. As a human, it would take you within seconds to learn how to play the ...
- 3,787
29
votes
What is the intuition behind the dot product attention?
Let's start with a bit of notation and a couple of important clarifications.
$\mathbf{Q}$ refers to the query vectors matrix, $q_i$ being a single query vector associated with a single input word.
$\...
- 5,218
18
votes
Why do most deep learning papers not include an implementation?
The paper's authors needed to implement their models anyway in order to conduct their experimentations, so why not publish the implementation?
Some papers and authors actually provide a link to their ...
- 39.6k
12
votes
Where can I find the original paper that introduced RNNs?
The two tech reports below both call RNNs explicitly "recurrent net(work)s".
Rumelhart, David E; Hinton, Geoffrey E, and Williams, Ronald J (Sept. 1985). Learning internal representations ...
- 221
9
votes
Accepted
What are some resources on computational learning theory?
Although I have only partially read or not read at all some of the following resources and some of these resources may not cover more advanced topics than the ones presented in the book you are ...
- 39.6k
8
votes
Accepted
What is different in each head of a multi-head attention mechanism?
The reason each head is different is because they each learn a different set of weight matrices $\{ W_i^Q, W_i^K, W_i^V \}$ where $i$ is the index of the head. To clarify, the input to each attention ...
- 1,510
8
votes
Accepted
How to express a fully connected neural network succintly using linear algebra?
The equation $$\hat{y} = \sigma(xW_\color{green}{1})W_\color{blue}{2} \tag{1}\label{1}$$ is the equation of the forward pass of a single-hidden layer fully connected and feedforward neural network, i....
- 39.6k
7
votes
Accepted
What if the more fit parent has fewer nodes compared to the other, will the disjoint and excess genes be discarded?
When crossover happens and one parent is fitter than the other, the nodes from the more fit parent are carried over to the child. This is the case as disjoint and excess genes are only carried over ...
- 193
7
votes
What is sample efficiency, and how can importance sampling be used to achieve it?
Sample Efficiency denotes the amount of experience that an agent/algorithm needs to generate in an environment (e.g. the number of actions it takes and number of resulting states + rewards it observes)...
- 10.1k
6
votes
Where to publish a first article in Deep Reinforcement Learning?
One important consideration here: in the last decade or two the machine learning and artificial intelligence fields, which contains the majority of reinforcement learning work, researchers have ...
- 161
6
votes
Accepted
If vanishing gradients are NOT the problem that ResNets solve, then what is the explanation behind ResNet success?
They explained in the paper why they introduce residual blocks. They argue that it's easier to learn residual functions $F(x) = H(x) - x$ and then add them to the original representation $x$ to get ...
- 2,336
6
votes
Why do most deep learning papers not include an implementation?
Someone can argue to some human adequate reasons, but there is a bad trend of falsified results in deep learning research papers that propose some nowel solutions or even update state-of-the-art model ...
6
votes
Why do most deep learning papers not include an implementation?
The first reason described in nbro's answer can definitely be an important one; authors may have implemented their software using code that they can't share. There's a lot of research coming out of ...
- 10.1k
6
votes
Accepted
What is a filter in the context of graph convolutional networks?
Short answer
Check out the paper of Shuman et al. [1], it provides some background on Graph Signal Processing, including answers to your questions in sections II.C and III.A
Long Answer
Question 1
Yes,...
5
votes
Where to publish a first article in Deep Reinforcement Learning?
I recommend you focus on quality over quantity. Publishing a paper will boost your reputation and make you more recognised within your academic field (AI); however, this is only if the paper provides ...
- 1,186
5
votes
Where can I find the original paper that introduced RNNs?
Hopfield networks, a special case of RNNs, were first proposed in 1982: https://www.pnas.org/content/79/8/2554
Otherwise (shameless plug, I am the author) a non-technical timeline for NLP can be found ...
- 196
5
votes
Accepted
How is inequality 31 derived from equality 30 in lemma 2 of the "Trust Region Policy Optimization" paper?
We can start with equation (30):
$$
\bar{A}(s) = P(a \neq \tilde{a}) \mathbb{E}_{(a,\tilde{a})\sim(\pi,\tilde{\pi}|a\neq\tilde{a})} [A_\pi(s, \tilde{a}) - A_\pi(s, a)]
$$
Taking the absolute value ...
- 101
5
votes
Why are reinforcement learning methods sample inefficient?
I will try to give a broad answer, if it's not helpful I'll remove it.
When we talk about sampling we are actually talking about the number of interaction required to an agent to learn a good model ...
- 5,218
5
votes
What are some alternatives to "Papers with Code"?
Recently arxiv.org added a Code Tab towards the end of paper descriptions. Which contains links to both the official and community code.
I don't know if this is the case for all the papers or not ...
- 764
5
votes
Accepted
What does "semantic gap" mean?
In terms of transfer learning, semantic gap means different meanings and purposes behind the same syntax between two or more domains. For example, suppose that we have a deep learning application to ...
- 1,751
5
votes
Accepted
Does higher FLOPS mean higher throughput?
In the context of Deeplearning:
FLOPS: Floating Point Ops per Second
FLOPs: Floating Point Ops
FLOPS, refers to the number of floating point operations that can be performed by a computing entity in ...
4
votes
Accepted
Why do we need 10 bits to represent the 1000 classes in AlexNet?
You need 10-bits ($2^{10} = 1024$) to represent 1000 classes.
- 1,863
4
votes
How would DeepMind's new differentiable neural computer scale?
Examining the architecture of the DNC indeed shows many similarities to the LSTM. Consider the diagram in the DeepMind article that you linked to:
Compare this to the LSTM architecture (credit to ...
- 251
4
votes
Are there human predictions of when a computer would have been better than a human at Go?
Go predictions were included in the paper:
The experts are far from infallible. They predicted that AI would be better than humans at Go by about 2027. (This was in 2015, remember.) SOURCE: Experts ...
- 6,237
4
votes
What are some books or state of the art papers about the development of a strong-AI?
There is actually a book called Artificial General Intelligence by Ben Goertzel and Cassio Pennachin. It's a bit out of date (from 2008), and published as a Springer-Verlag monograph (which tends to ...
- 9,207
4
votes
Accepted
What does "we wrap the individual and reuse the codons" mean in the paper "Grammatical Evolution" by Neill and Ryan?
In GE, the genotype is a linear sequence of codons. By "wrapping" it, you make it a circular sequence that never ends. It allows you to build a bigger tree, while having only a few codons. ...
- 156
4
votes
Where can I find the original paper that introduced RNNs?
Warren McCulloch and Walter Pitts talk about recurrent neural nets in their paper McCulloch, W.S., Pitts, W. A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical ...
4
votes
Accepted
What happens before the first 8 moves in Alpha Zero?
On page 13, right under Table S1 in the linked paper, this is explained (emphasis in bold at the end mine):
Each set of planes represents the board position at a time-step $t - T + 1, \dots, t$, ...
- 10.1k
4
votes
Accepted
What knowledge is required for understanding the AlphaZero paper?
The more you read, the more deeply you can understand any paper, but given your stated background, reading the Monte-Carlo Tree Search chapter of Barto & Sutton, plus Gerald Tesauro's TD-Gammon ...
- 9,207
Only top scored, non community-wiki answers of a minimum length are eligible