Most Popular
1500 questions
7
votes
3 answers
Would AlphaGo Zero become perfect with enough training time?
Would AlphaGo Zero become theoretically perfect with enough training time? If not, what would be the limiting factor?
(By perfect, I mean it always wins the game if possible, even against another perfect opponent.)
Christopher King
- 271
- 1
- 8
7
votes
3 answers
Is there research that employs realistic models of neurons?
Is there research that employs realistic models of neurons? Usually, the model of a neuron for a neural network is quite simple as opposed to the realistic neuron, which involves hundreds of proteins and millions of molecules (or even greater…
TomR
- 903
- 6
- 18
7
votes
1 answer
How does the Dempster-Shafer theory differ from Bayesian reasoning?
How does the Dempster-Shafer theory differ from Bayesian reasoning? How do these two methods handle uncertainty and compute posterior distributions?
rudresh dwivedi
- 171
- 1
- 3
7
votes
1 answer
In imitation learning, do you simply inject optimal tuples of experience $(s, a, r, s')$ into your experience replay buffer?
Due to my RL algorithm having difficulties learning some control actions, I've decided to use imitation learning/apprenticeship learning to guide my RL to perform the optimal actions. I've read a few articles on the subject and just want to confirm…
Rui Nian
- 433
- 4
- 13
7
votes
2 answers
What are the best machine learning models for music composition?
What are the best machine learning models that have been used to compose music? Are there some good research papers (or books) on this topic out there?
I would say, if I use a neural network, I would opt for a recurrent one, because it needs to have…
Ben
- 455
- 3
- 11
7
votes
2 answers
Why is the log probability replaced with the importance sampling in the loss function?
In the Trust-Region Policy Optimisation (TRPO) algorithm (and subsequently in PPO also), I do not understand the motivation behind replacing the log probability term from standard policy gradients
$$L^{PG}(\theta) = \hat{\mathbb{E}}_t[\log…
Mark
- 106
- 4
7
votes
1 answer
What makes multi-layer neural networks able to perform nonlinear operations?
As I know, a single layer neural network can only do linear operations, but multilayered ones can.
Also, I recently learned that finite matrices/tensors, which are used in many neural networks, can only represent linear operations.
However,…
Hyeonseo Yang
- 173
- 6
7
votes
1 answer
What is the relation between an environment, a state and a model?
In particular, I would like to have a simple definition of "environment" and "state". What are the differences between those two concepts? Also, I would like to know how the concept of model relates to the other two.
There is a similar question…
Diego Orellana
- 383
- 3
- 10
7
votes
3 answers
More effective way to improve the heuristics of an AI... evolution or testing between thousands of pre-determined sets of heuristics?
I'm making a Connect Four game where my engine uses Minimax with Alpha-Beta pruning to search. Since Alpha-Beta pruning is much more effective when it looks at the best moves first (since then it can prune branches of poor moves), I'm trying to come…
Inertial Ignorance
- 511
- 3
- 14
7
votes
2 answers
How does rotating an image and adding new 'rotated classes' prevent overfitting?
From Meta-Learning with Memory-Augmented Neural Networks in section 4.1:
To reduce the risk of overfitting, we performed data augmentation by randomly translating and rotating character images. We also created new classes through 90◦, 180◦ and 270◦…
AAC
- 171
- 1
- 2
7
votes
1 answer
For each epoch, can I use only on a subset of the full training dataset to train the neural network?
If one has a dataset large enough to learn a highly complex function, say learning chess game-play, and the processing time to run mini-batch gradient descent on this entire dataset is too high, can I instead do the following?
Run the algorithm on…
pranav
- 301
- 1
- 9
7
votes
3 answers
An AI that asks questions?
Typical AI these days are question-answering machines. For example, Siri, Alexa and Google Home. But it is always the human asking the questions and the AI answering.
Are there any good examples of an AI that is curious and asks questions of its…
zooby
- 2,260
- 1
- 14
- 22
7
votes
3 answers
CNN's vs Densely Connected NN's
In image classification we are generally told the main reason of using CNN's is that densely connected NN's cannot handle so many parameters (10 ^ 6 for a 1000 * 1000 image). My question is, is there any other reason why CNN's are used over DNN's…
user9947
7
votes
1 answer
How is division by zero avoided when implementing back-propagation for a neural network with sigmoid at the output neuron?
I am building a neural network for which I am using the sigmoid function as the activation function for the single output neuron at the end. Since the sigmoid function is known to take any number and return a value between 0 and 1, this is causing…
Dimitry
- 73
- 1
- 3
7
votes
2 answers
Are humans intelligent according to the definition of an intelligent agent?
Given the following definition of an intelligent agent (taken from a Wikipedia article)
If an agent acts so as to maximize the expected value of a performance measure based on past experience and knowledge then it is intelligent
and given that we,…
wythagoras
- 1,521
- 12
- 28