Most Popular
1500 questions
5
votes
1 answer
When do mutations in NEAT occur?
I read through the Evolving Neural Networks through Augmenting Topologies (NEAT) paper. I understand the algorithm now, but one thing is still unclear to me.
When does the mutation occur and how does it take place? How is it chosen whether to add a…
Miemels
- 389
- 2
- 10
5
votes
3 answers
In Q-learning, wouldn't it be better to simply iterate through all possible states?
In Q-learning, all resources I've found seem to say that the algorithm to update the Q-table should start at some initial state, and pick actions (which are sometimes random) to explore the state space.
However, wouldn't it be better/faster/more…
Kricket
- 197
- 4
5
votes
1 answer
Use ConvNet to predict bitmap
I want to build a classifier which takes an aerial image and outputs a bitmap. The bitmap is supposed to be 1 at every pixel where the aerial image has water. For this process I want to use a ConvNet but I am unsure about the output layer. I…
treigerm
- 53
- 2
5
votes
1 answer
Are there any approaches to AGI that will definitely not work?
Is there empirical evidence that some approaches to achieving AGI will definitely not work? For the purposes of the question the system should at least be able to learn and solve novel problems.
Some possible approaches:
A Prolog program
A program…
persiflage
- 153
- 4
5
votes
2 answers
Feasibility of generating large images with a convnet
I've spent the past couple of months learning about neural networks, and am thinking of projects that would be fun to work on to cement my understanding of this tech.
One thing that came to mind last night is a system that takes an image of a movie…
JR Heard
- 98
- 5
5
votes
1 answer
Do AlphaZero/MuZero learn faster in terms of number of games played than humans?
I don't know much about AI and am just curious.
From what I read, AlphaZero/MuZero outperform any human chess player after a few hours of training. I have no idea how many chess games a very talented human chess player on average has played before…
220284
- 153
- 4
5
votes
1 answer
What should the initial UCT value be with MCTS, when leaf's simulation count is zero? Infinity?
I am implenting a Monte Carlo Tree Search algorithm, where the selection process is done through Upper Confidence Bound formula:
def uct(state):
log_n = math.log(state.parent.sim_count)
explore_term = self.exploration_weight *…
semyd
- 153
- 1
- 5
5
votes
1 answer
How do I design a neural network that breaks a 5-letter word into its corresponding syllables?
I am going to design a neural network which will be able to break a 5-letter word into its corresponding syllables (hybrid syllables, I mean it will not strictly adhere to grammatical syllable rules but will be based on some training sets I…
Programmer
- 164
- 6
5
votes
2 answers
Is it really possible to create the "Perfect Cylinder" used in Universal Approximation Theorem for 1-hidden layer Neural Network?
There are proofs for the universal approximation theorem with just 1 hidden layer.
The proof goes like this:
Create a "bump" function using 2 neurons.
Create (infinitely) many of these step functions with different angles in order to create a…
KoKlA
- 133
- 6
5
votes
1 answer
Why does regular Q-learning (and DQN) overestimate the Q values?
The motivation for the introduction of double DQN (and double Q-learning) is that the regular Q-learning (or DQN) can overestimate the Q value, but is there a brief explanation as to why it is overestimated?
ground clown
- 111
- 2
5
votes
1 answer
Can games be solved without an evaluation function?
Fundamentally, a game-playing AI must solve the problem of choosing the best action from a set of possible actions.
Most existing game AI's, such as AlphaGo, do this by using an evaluation function, which maps game states to real numbers. The real…
dshin
- 161
- 5
5
votes
1 answer
Research into social behavior in Prisoner's Dilemma
I've been working on research into reproducing social behavior using multi-agent reinforcement learning. My focus has been on a GridWorld-style game, but I was thinking that maybe a simpler Prisoner's Dilemma game could be a better approach. I tried…
Ram Rachum
- 261
- 1
- 9
5
votes
1 answer
Why do we need importance sampling?
I was studying the off-policy policy improvement method. Then I encountered importance sampling. I completely understood the mathematics behind the calculation, but I am wondering what is the practical example of importance sampling.
For instance,…
Alireza Hosseini
- 51
- 2
5
votes
1 answer
What's the difference between content-based attention and dot-product attention?
I'm following this blog post which enumerates the various types of attention.
It mentions content-based attention where the alignment scoring function for the $j$th encoder hidden state with respect to the $i$th context vector is the cosine…
Alexander Soare
- 1,319
- 2
- 11
- 26
5
votes
2 answers
How does AlphaZero's MCTS work when starting from the root node?
From the AlphaGo Zero paper, during MCTS, statistics for each new node are initialized as such:
${N(s_L, a) = 0, W (s_L, a) = 0, Q(s_L, a) = 0, P (s_L, a) = p_a}$.
The PUCT algorithm for selecting the best child node is $a_t = argmax(Q(s,a) +…
sb3
- 137
- 7