Most Popular
1500 questions
5
votes
0 answers
What is the justification for Kaiming He initialization?
I've been trying to understand where the formulas for Xavier and Kaiming He initialization come from. My understanding is that these initialization schemes come from a desire to keep the gradients stable during back-propagation (avoiding…
Jack M
- 262
- 2
- 9
5
votes
1 answer
Is reinforcement learning only about determining the value function?
I started reading some reinforcement learning literature, and it seems to me that all approaches to solving reinforcement learning problems are about finding the value function (state-value function or action-state value function).
Are there any…
Felix P.
- 297
- 1
- 6
5
votes
1 answer
Is there an efficient way to implement a random crossover of individuals stored in a matrix?
I am using a GA to optimise an ANN in Matlab. This ANN is pretty basic (input, hidden, output) but the input size is quite large (10,000) and the output size is 2 since I have to classes of images to be classified.
The weights are in the form of 2…
user3952
- 51
- 2
5
votes
3 answers
Has an AI ever solved a detective mystery?
In detective novels, the point is often that the reader gets enough information to solve the crime themselves. This "puzzle" aspect of detective novels is part of the attraction.
Often the difficulty for humans is to keep track of all the variables…
S.L. Barth is on codidact.com
- 1,214
- 1
- 10
- 21
5
votes
1 answer
When should we use separable convolution?
I was reading the "Deep Learning with Python" by François Chollet. He mentioned separable convolution as following
This is equivalent to separating the learning of spatial features and
the learning of channel-wise features, which makes a lot of…
Enes
- 314
- 3
- 11
5
votes
2 answers
What is the advantage of using cross entropy loss & softmax?
I am trying to do the standard MNIST dataset image recognition test with a standard feed forward NN, but my network failed pretty badly. Now I have debugged it quite a lot and found & fixed some errors, but I had a few more ideas. For one, I am…
Ben
- 435
- 3
- 11
5
votes
1 answer
Is the state transition matrix known to the agents in a Markov decision processes?
The question is more or less in the title.
A Markov decision process consists of a state space, a set of actions, the transition probabilities and the reward function. If I now take an agent's point of view, does this agent "know" the transition…
Felix P.
- 297
- 1
- 6
5
votes
1 answer
What is the loss for policy gradients with continuous actions?
I know with policy gradients used in an environment with a discrete action space are updated with $$
\Delta \theta_{t}=\alpha \nabla_{\theta} \log \pi_{\theta}\left(a_{t} \mid s_{t}\right) v_{t}
$$
where $v_t$ could be many things that represent how…
S2673
- 590
- 4
- 17
5
votes
3 answers
Why neural networks tend to be trained to recognize multiple things instead of just one?
I was watching this series: https://www.youtube.com/watch?v=aircAruvnKk
The series demonstrates neural networks by building a simple number recognizing network.
It got me thinking: Why neural networks try to recognize multiple labels instead of just…
Ville
- 151
- 2
5
votes
3 answers
How do weak learners become strong in boosting?
Boosting refers to a family of algorithms which converts weak learners to strong learners. How does it happen?
Legend
- 103
- 3
5
votes
1 answer
Using ConceptNet5 to find similar systems to solve specific problems?
I installed a locally running instance of the ConceptNet5 knowledgebase in an elasticsearch server. I used this data to implement the so-called "Analogietechnik" (a creativity technique to solve a problem from the perspective of another system) as…
hardking
- 59
- 2
5
votes
1 answer
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 artificial neural networks? For example, a chip which…
kenorb
- 10,483
- 3
- 44
- 94
5
votes
4 answers
How can an artificial general intelligence determine which information is true?
After the explosion of fake news during the US election, and following the question about whether AIs can educate themselves via the internet, it is clear to me that any newly-launched AI will have a serious problem knowing what to believe (that is,…
Jnani Jenny Hale
- 521
- 2
- 11
5
votes
2 answers
What is the weight matrix in self-attention?
I've been looking into self-attention lately, and in the articles that I've been seeing, they all talk about "weights" in attention. My understanding is that the weights in self-attention are not the same as the weights in a neural network.
From…
Mark
- 233
- 1
- 6
5
votes
1 answer
What's the optimal policy in the rock-paper-scissors game?
A deterministic policy in the rock-paper-scissors game can be easily exploited by the opponent - by doing just the right sequence of moves to defeat the agent. More often than not, I've heard that a random policy is the optimal policy in this case -…
stoic-santiago
- 1,141
- 8
- 19