Community Digest

Top new questions this week:

What is the difference between Q-learning, Deep Q-learning and Deep Q-network?

Q-learning uses a table to store all state-action pairs. Q-learning is a model-free RL algorithm, so how could there be the one called Deep Q-learning, as deep means using DNN; or maybe the state-...

reinforcement-learning comparison q-learning dqn deep-rl  
asked by datdinhquoc 8 votes
answered by David Ireland 5 votes

Why is my GAN more unstable with bigger networks?

I am working with generative adversarial networks (GANs) and one of my aims at the moment is to reproduce samples in two dimensions that are distributed according to a circle (see animation). When ...

neural-networks machine-learning deep-learning generative-adversarial-networks heuristics  
asked by Mafu 5 votes

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 ...

comparison training alphazero chess muzero  
asked by 220284 4 votes

How should we regularize an LSTM model?

There are five parameters from an LSTM layer for regularization if I am correct. To deal with overfitting, I would start with reducing the layers reducing the hidden units Applying dropout or ...

recurrent-neural-networks long-short-term-memory overfitting regularization dropout  
asked by Leo 3 votes
answered by Faran Khalid 0 votes

How should I implement the state transition when it is a Gaussian distribution?

I am reading this paper Anxiety, Avoidance and Sequential Evaluation and is confused about the implementation of a specific lab study. Namely, the authors model what is called the Balloon task using a ...

reinforcement-learning markov-decision-process implementation temporal-difference-methods transition-model  
asked by dezdichado 3 votes

Does DQN generalise to unseen states in the case of discrete state-spaces?

In my understanding, DQN is useful because it utilises a neural network as a q-value function approximator, which, after the training, can generalise to unseen states. I understand how that would work ...

reinforcement-learning dqn deep-rl generalization discrete-state-spaces  
asked by Redox 3 votes

Is non-negative matrix factorization for machine learning obsolete?

I am taking a course about using matrix factorization for machine learning. The first thing that came into my mind is by using the matrix factorization we are always limited to linear relationships ...

neural-networks machine-learning reference-request applications  
asked by Rami ZK 3 votes

Greatest hits from previous weeks:

In a CNN, does each new filter have different weights for each input channel, or are the same weights of each filter used across input channels?

My understanding is that the convolutional layer of a convolutional neural network has four dimensions: input_channels, filter_height, filter_width, number_of_filters. Furthermore, it is my ...

deep-learning convolutional-neural-networks image-recognition  
asked by Ryan Chase 46 votes
answered by Mohsin Bukhari 18 votes

What is an objective function?

Local search algorithms are useful for solving pure optimization problems, in which the aim is to find the best state according to an objective function. My question is what is the objective function?

terminology loss-functions optimization local-search meta-heuristics  
asked by Abbas Ali 3 votes
answered by nbro 3 votes

How does LSTM in deep reinforcement learning differ from experience replay?

In the paper Deep Recurrent Q-Learning for Partially Observable MDPs, the author processed the Atari game frames with an LSTM layer at the end. My questions are: How does this method differ from the ...

reinforcement-learning long-short-term-memory deep-rl comparison experience-replay  
asked by Kevin. Fang 14 votes
answered by Neil Slater 14 votes

What is the difference between strong-AI and weak-AI?

I've heard the terms strong-AI and weak-AI used. Are these well defined terms or subjective ones? How are they generally defined?

terminology definitions agi comparison weak-ai  
asked by WilliamKF 43 votes
answered by jrmyp 35 votes

How do I choose the best algorithm for a board game like checkers?

How do I choose the best algorithm for a board game like checkers? So far, I have considered only three algorithms, namely, minimax, alpha-beta pruning, and Monte Carlo tree search (MCTS). Apparently,...

game-ai applications monte-carlo-tree-search minimax alpha-beta-pruning  
asked by Joey 16 votes
answered by John Doucette 19 votes

Teach a Neural Network to play a card game

I am currently writing an engine to play a card game, as there is no engine yet for this particular game. I am hoping to be able to introduce a neural net to the game afterwards, and have it learn to ...

neural-networks machine-learning gaming neat  
asked by pcaston2 11 votes
answered by Ben Hutchison 3 votes

How could artificial intelligence harm us?

We often hear that artificial intelligence may harm or even kill humans, so it might prove dangerous. How could artificial intelligence harm us?

philosophy social neo-luddism  
asked by Manak 54 votes
answered by Djib2011 50 votes

Can you answer these questions?

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 ...

asked by persiflage 2 votes

CSP heuristic to simultaneously reduce conflicts and find near optimal assignment

I am trying to design a good heuristic to solve a constraint satisfaction problem (CSP). I think that a possible heuristic to use is $$h_1(\text{state}) = \text{number of conflicts in state}$$ However,...

heuristics constraint-satisfaction-problems local-search  
asked by bobby brown 1 vote

What are some of the main high level approaches to applying ML on kinematic sensor data?

I've just started a project which will involve having to detect certain events in a stream of kinematic sensor data. By searching through the literature, I've found a lot of highly specific papers, ...

machine-learning reference-request signal-processing  
asked by Alexander Soare 2 votes
You're receiving this message because you subscribed to the Artificial Intelligence community digest.
Unsubscribe from this community digest       Edit email settings       Leave feedback       Privacy
Stack Overflow

Stack Overflow, 110 William Street, 28th floor, New York, NY 10038