Most Popular
1500 questions
8
votes
2 answers
How can I translate a natural language question to an MDX query?
I am researching Natural Language Processing (NLP) to develop an NL Question Answering system. The answering part is already done. So processing the question remains, along with the questions regarding the algorithms.
The final product should allow…
lilienfa
- 319
- 1
- 9
8
votes
3 answers
What programmable devices can be used to teach artificial intelligence?
Could you give examples of affordable programmable devices that could be used in university classes to teach students about A.I. and demonstrate it?
The devices are expected to do some form of self-learning, pattern recognition, or any other…
Jason Lobo
- 81
- 1
8
votes
1 answer
How do we decide which membership function to use?
In classical set theory, there are two options for an element. It is either a member of a set or not. But in fuzzy set theory, there are membership functions to define the "rate" of an element being a member of a set. In other words, classical logic…
buzzer
- 99
- 2
- 10
8
votes
1 answer
How to fill in missing transitions when sampling an MDP transition table?
I have a simulator modelling a relatively complex scenario. I extract ~12 discrete features from the simulator state which forms the basis for my MDP state space.
Suppose I am estimating the transition table for an MDP by running a large number of…
Brendan Hill
- 263
- 1
- 6
8
votes
5 answers
Linear regression: why is distance *squared* used as an error metric?
Usually when performing linear regression predictions and gradient descent, the measure of the level of error for a particular line will be measured by the sum of the squared-distance values.
Why distance squared?
In most of the explanations I…
Alpha
- 458
- 3
- 12
8
votes
2 answers
Apart from Reinforcement Learning, are there any other machine learning approaches to play video games?
OpenAI's Universe utilizes RL algorithms. I also know that Q-learning has been used to solve some games.
Are there any other ML approaches to solve games? For example, could we use genetic algorithms to develop agents that solve games?
U754V
- 83
- 5
8
votes
1 answer
What is ergodicity in a Markov Decision Process (MDP)?
I have read about the concept of ergodicity on the safe RL paper by Moldovan (section 3.2) and the RL book by Sutton (chapter 10.3, 2nd paragraph).
The first one says that "a belief over MDPs is ergodic if and only if any state is reachable from any…
josealeixo.pc
- 215
- 2
- 6
8
votes
2 answers
Could humans hurt a conscious or sentient AI?
If a conscious AI is possible, would it also be possible for someone who knows what they are doing to torture (or hurt) the AI? Could this be avoided? How?
This question deals with computer-based AI, not robots, which are as conscious as people…
Destructible Lemon
- 189
- 4
8
votes
2 answers
What is the relation between the context in contextual bandits and the state in reinforcement learning?
Conceptually, in general, how is the context being handled in contextual bandits (CB), compared to states in reinforcement learning (RL)?
Specifically, in RL, we can use a function approximator (e.g. a neural network) to generalize to other states.…
Maxim Volgin
- 183
- 2
- 8
8
votes
3 answers
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 regularizers.
There are kernel_regularizer,…
Leo
- 133
- 1
- 6
8
votes
1 answer
Validation accuracy higher than training accurarcy
I implemented the unet in TensorFlow for the segmentation of MRI images of the thigh. I noticed I always get a higher validation accuracy by a small gap, independently of the initial split. One example:
So I researched when this could be…
Lis Louise
- 139
- 4
8
votes
1 answer
Why is there a Uniform and Normal version of He / Xavier initialization in DL libraries?
Two of the most popular initialization schemes for neural network weights today are Xavier and He. Both methods propose random weight initialization with a variance dependent on the number of input and output units. Xavier proposes
$$W \sim…
Tinu
- 628
- 1
- 4
- 12
8
votes
2 answers
Why is KL divergence used so often in Machine Learning?
The KL Divergence is quite easy to compute in closed form for simple distributions -such as Gaussians- but has some not-very-nice properties. For example, it is not symmetrical (thus it is not a metric) and it does not respect the triangular…
Federico Taschin
- 253
- 2
- 7
8
votes
1 answer
How is the DQN loss derived from (or theoretically motivated by) the Bellman equation, and how is it related to the Q-learning update?
I'm doing a project on Reinforcement Learning. I programmed an agent that uses DDQN. There are a lot of tutorials on that, so the code implementation was not that hard.
However, I have problems understanding how one should come up with this kind of…
Yves Boutellier
- 183
- 6
8
votes
2 answers
What is the difference between the positional encoding techniques of the Transformer and GPT?
I know the original Transformer and the GPT (1-3) use two slightly different positional encoding techniques.
More specifically, in GPT they say positional encoding is learned. What does that mean? OpenAI's papers don't go into detail very much.
How…
Leevo
- 305
- 2
- 9