Most Popular
1500 questions
7
votes
1 answer
What are the conditions of convergence of temporal-difference learning?
In reinforcement learning, temporal difference seem to update the value function in each new iteration of experience absorbed from the environment.
What would be the conditions for temporal-difference learning to converge in the end? How is it…
MJeremy
- 173
- 1
- 3
7
votes
2 answers
What is the difference between a Bayesian Network and a Markov Chain?
I am trying to understand the difference between a Bayesian Network and a Markov Chain.
When I search for this one the web, the unanimous solution seems to be that a Bayesian Network is directional (i.e. it's a DAG) and a Markov Chain is not…
Newskooler
- 173
- 6
7
votes
1 answer
What is the most abstract concept learned by a deep neural network?
It seems that deep neural networks are making improvements largely because as we add nodes and connections, they are able to put together more and more abstract concepts. We know that, starting from pixels, they start to recognize high level objects…
alwaysLearningABC
- 271
- 1
- 5
7
votes
2 answers
Does the "lowest layer" refer to the first or last layer of the neural network?
People sometimes use 1st layer, 2nd layer to refer to a specific layer in a neural net. Is the layer immediately follows the input layer called 1st layer?
How about the lowest layer and highest layer?
Piete3r
- 227
- 2
- 5
7
votes
2 answers
Why AlphaGo didn't use Deep Q-Learning?
In the previous research, in 2015, Deep Q-Learning shows its great performance on single player Atari Games. But why do AlphaGo's researchers use CNN + MCTS instead of Deep Q-Learning? is that because Deep Q-Learning somehow is not suitable for Go?
malioboro
- 2,859
- 3
- 23
- 47
7
votes
2 answers
How would "wisdom" be defined in AI?
For years, I have been dealing with (and teaching) Knowledge Representation and Knowledge Representation languages. I just discovered that in another community (Information Systems and the such) there is something called the "DIKW pyramid" where…
yannis
- 171
- 2
7
votes
2 answers
Why does TensorFlow docs discourage using softmax as activation for the last layer?
The beginner colab example for tensorflow states:
Note: It is possible to bake this tf.nn.softmax in as the activation function for the last layer of the network. While this can make the model output more directly interpretable, this approach is…
galah92
- 173
- 5
7
votes
2 answers
Why is creating an AI that can code a hard task?
For people who have experience in the field, why is creating AI that has the ability to write programs (that are syntactically correct and useful) a hard task?
What are the barriers/problems we have to solve before we can solve this problem? If you…
Landon G
- 500
- 2
- 10
7
votes
2 answers
Aren't all discrete convolutions (not just 2D) linear transforms?
The image above, a screenshot from this article, describes discrete 2D convolutions as linear transforms. The idea used, as far as I understand, is to represent the 2 dimensional $n$x$n$ input grid as a vector of $n^2$ length, and the $m$x$m$…
stoic-santiago
- 1,201
- 9
- 22
7
votes
3 answers
What kind of road and weather conditions can a self-driving car deal with?
Can self-driving cars deal with snow, heavy rain, or other weather conditions like these? Can they deal with unusual events, such as ducks on the road?
liori
- 513
- 2
- 9
7
votes
2 answers
What was the first machine that was able to carry on a conversation?
What was the first AI that was able to carry on a conversation, with real responses, such as in the famous 'I am not a robot. I am a unicorn' case?
A 'real response' constitutes a sort-of personalized answer to a specific input by a user.
Mithical
- 2,965
- 5
- 28
- 39
7
votes
1 answer
How should the neural network deal with unexpected inputs?
I recently wrote an application using a deep learning model designed to classify inputs. There are plenty of examples of this using images of irises, cats, and other objects.
If I trained a data model to identify and classify different types of…
Jeff
- 173
- 5
7
votes
2 answers
Interpretation of inverse matrix in mean calculation in Gaussian Process
The formula for mean prediction using Gaussian Process is $k(x_*, x)k(x, x)^{-1}y$, where $k$ is the covariance function. See e.g. equation 2.23 (in chapter 2) from Gaussian Processes for Machine Learning (2006) by C. E. Rasmussen & C. K. I.…
Kasia
- 303
- 2
- 9
7
votes
2 answers
Why are reinforcement learning methods sample inefficient?
Reinforcement learning methods are considered to be extremely sample inefficient.
For example, in a recent DeepMind paper by Hessel et al., they showed that in order to reach human-level performance on an Atari game running at 60 frames per second…
rrz0
- 273
- 2
- 7
7
votes
2 answers
Does a quantum computer resolve the halting problem and would that advance strong AI?
Have there been proposed extensions to go beyond a Turing machine that solve the halting problem and if so, would those proposed extensions have value to advance strong Artificial Intelligence? For example, does quantum computing go beyond the…
WilliamKF
- 2,533
- 1
- 26
- 31