Artificial Intelligence Stack Exchange
Artificial Intelligence Stack Exchange

Most Popular

more tags
1500 questions
5
votes
1 answer

My DQN is stuck and can't see where the problem is

I'm trying to replicate the DeepMind paper results, so I implemented my own DQN. I left it training for more than 4 million frames (more than 2000 episodes) on SpaceInvaders-v4 (OpenAI-Gym) and it couldn't finish a full episode. I tried two…
JCP
  • 173
  • 12
5
votes
1 answer

Expected SARSA vs SARSA in "RL: An Introduction"

Sutton and Barto state in the 2018-version of "Reinforcement Learning: An Introduction" in the context of Expected SARSA (p. 133) the following sentences: Expected SARSA is more complex computationally than Sarsa but, in return, it eliminates the…
F.M.F.
  • 311
  • 3
  • 7
5
votes
1 answer

Can (trained) neural networks be combined with symbolic AI to perform operations like AND?

Does anyone work out ways of relating trained neural networks by symbolic AI? For example, if I train a network on pictures of dogs, and I train a network on pictures of shirts. You could imagine that the simplest way (without going through the…
Steven Sagona
  • 221
  • 3
  • 8
5
votes
1 answer

Should I model my problem as a semi-MDP?

I have a system (like a bank) that people (customers) are entered into the systems by a Poisson process, so the time between the arrival of people (two consecutive customers) will be a random variable. The state of the problem is related to just the…
Amin
  • 471
  • 2
  • 11
5
votes
2 answers

When is a knowledge base consistent?

I am studying a knowledge base (KB) from the book "Artificial Intelligence: A Modern Approach" (by Stuart Russell and Peter Norvig) and from this series of slides. A formula is satisfiable if there is some assignment to the variables that makes the…
theantomc
  • 263
  • 2
  • 8
5
votes
1 answer

What are some examples of Classical AI applications?

I believe that Classical AI uses deductive thought processes. For example, given as a set of constraints, deduce a conclusion. What are some examples of successfully applying Classical AI to real-world problems?
WilliamKF
  • 2,493
  • 1
  • 24
  • 31
5
votes
1 answer

Is it possible to recognise a person based on what they have written?

I needed to make a system for recognizing people based on hundreds of texts by finding similarities in their written text grammatically or similarities between words they choose for writing. I don't want it so accurate, but I wanted to know if it is…
Stick
  • 53
  • 4
5
votes
3 answers

How can a neural network learn when the derivative of the activation function is 0?

Imagine that I have an artificial neural network with a single hidden layer and that I am using ReLU as my activating function. If by change I initialize my bias and my weights in such a form that: $$ X * W + B < 0 $$ for every input x in X then the…
Daniel Oliveira
  • 205
  • 1
  • 4
5
votes
1 answer

What is a "logit probability"?

DeepMind's paper "Mastering the game of Go without human knowledge" states in its "Methods" section on its "Neural network architecture" that the output layer of AlphaGo Zero's policy head is "A fully connected linear layer that outputs a vector of…
sadakatsu
  • 153
  • 3
5
votes
1 answer

How do I compute the variance of the return of an evaluation policy using two behaviour policies?

Suppose there is an evaluation policy called $\pi_{e}$ and there are two behavior policies $\pi_{b1}$ and $\pi_{b2}$. I know that it is possible to estimate the return of policy $\pi_{e}$ through behavior policies via importance sampling, which is…
Amin
  • 471
  • 2
  • 11
4
votes
1 answer

How data augmentation like rotation affects the quality of detection?

I'm using an object detection neural network and I employ data augmentation to increase a little my small dataset. More specifically I do rotation, translation, mirroring and rescaling. I notice that rotating an image (and thus it's bounding box)…
Louis Lac
  • 308
  • 2
  • 9
4
votes
2 answers

Handling emotion in informal text (Hi vs HIIIIII!!!!)?

This is a question related to Neural network to detect "spam"?. I'm wondering how it would be possible to handle the emotion conveyed in text. In informal writing, especially among a juvenile audience, it's usual to find emotion expressed as…
hjf
  • 201
  • 1
  • 6
4
votes
3 answers

What is an adversarial attack?

I'm reading this really interesting article CycleGAN, a Master of Steganography. I understand everything up until this paragraph: we may view the CycleGAN training procedure as continually mounting an adversarial attack on $G$, by optimizing a…
Cyclist
  • 41
  • 1
4
votes
1 answer

Why do neural nets and machine learning tend to work well with MCTS, but not with regular Minimax game-playing AI?

I've often heard MCTS grouped together with neural nets and machine learning. From what I gather, MCTS uses a refined intuition (from maching learning) to evaluate positions. This allows it to better guess which moves are worth playing out more. But…
Inertial Ignorance
  • 501
  • 3
  • 13
4
votes
2 answers

Neural network to detect "spam"?

I've inherited a neural network project at the company I work for. The person who developed gave me some very basic training to get up and running. I've maintained it for a while. The current neural network is able to classify messages for telcos:…
hjf
  • 201
  • 1
  • 6
1 2 3
…
99
100