Most Popular
1500 questions
5
votes
1 answer
Can you analyse a neural network to determine good states?
I've developed a neural network that can play a card game. I now want to use it to create decks for the game. My first thought would be to run a lot of games with random decks and use some approximation (maybe just a linear approximation with a…
OrangeMan
- 237
- 1
- 5
5
votes
1 answer
Is the discount not needed in a deterministic environment for Reinforcement Learning?
I'm now reading a book titled as "Deep Reinforcement Learning Hands-On" and the author said the following on the chapter about AlphaGo Zero:
Self-play
In AlphaGo Zero, the NN is used to approximate the prior probabilities of the actions and…
Blaszard
- 1,037
- 3
- 11
- 25
5
votes
1 answer
Which other loss functions for hierarchical multi-label classification could I use?
I am looking to try different loss functions for a hierarchical multi-label classification problem. So far, I have been training different models or submodels like multilayer perceptron (MLP) branch inside a bigger model which deals with different…
Skinish
- 163
- 1
- 1
- 9
5
votes
1 answer
Is there a database somewhere of common lists?
I'm looking for a database or some machine readable document that contains common ordered lists or common short sets. e.g:
{January, February, March,...}
{Monday, Tuesday, ....}
{Red, Orange, Yellow,...}
{1,2,3,4,...}
{one, two, three,…
zooby
- 2,206
- 1
- 13
- 22
5
votes
1 answer
How is the fitted Q-iteration algorithm related to $Q^*(s, a)$, and how can we use function approximation with this algorithm?
I hope to get some clarifications on Fitted Q-Iteration (FQI).
My Research So Far
I've read Sutton's book (specifically, ch 6 to 10), Ernst et al and this paper.
I know that $Q^*(s, a)$ expresses the expected value of first taking action $a$ from…
NoviceProg
- 153
- 4
5
votes
2 answers
How can I train a neural network for image classification when the dataset is small?
I need to train a convolutional neural network to classify snake images. The problem is that I have only a small number of images available for some snake types.
So, what is the best approach to train a neural network for image classification using…
Lakwin Chandula
- 51
- 3
5
votes
1 answer
How can I apply reinforcement learning to solve this asteroid game?
Introduction
An attractive asteroid game was described in the paper Learning Policies for Embodied Virtual Agents through Demonstration (2017, Jonathan Dinerstein et al.):
In our first experiment, the virtual agent is a spaceship pilot, The pilot's…
GIA
- 568
- 6
- 22
5
votes
3 answers
Can ML/AI understand incomplete constructs like humans?
We have AI's predicting images, predicting objects in an image. Understanding audio, meaning of the audio if it is a spoken sentence.
In humans when we start seeing a movie halfway through, we still understand the entire movie (although this might…
user9947
5
votes
1 answer
Is Christopher Bishop's "Pattern Recognition and Machine Learning" out of date in 2018?
I recently came across a reference to a book that was highly regarded: "Pattern Recognition and Machine Learning" by Christopher Bishop.
I am a beginner working my way through some machine learning courses on my own.
I'm curious if this book is…
Hanzy
- 519
- 3
- 11
5
votes
2 answers
Is the word "pose" used correctly in the paper "Matrix Capsules with EM Routing"?
In traditional computer vision and computer graphics, the pose matrix is a $4 \times 4$ matrix of the form
$$
\begin{bmatrix}
r_{11} & r_{12} & r_{12} & t_{1} \\
r_{21} & r_{22} & r_{22} & t_{2} \\
r_{31} & r_{32} & r_{32} & t_{3}…
bossman
- 163
- 4
5
votes
1 answer
What algorithms does stackoverflow use for classifying duplicate questions?
Can I get details about the algorithms used for classifying questions in stackoverflow ("Questions that may already have your answer"). Most of the suggestions I get are nowhere related to the question I have intended to ask.
thecomplexitytheorist
- 776
- 3
- 19
5
votes
4 answers
What kind of neural network architecture do I use to classify images into one hundred thousand classes?
I have an image dataset where objects may belong to one of the hundred thousand classes.
What kind of neural network architecture should I use in order to achieve this?
Mohsin
- 982
- 1
- 10
- 15
5
votes
1 answer
What is the importance of the endocannabinoid system for cognitive function?
The endocannabinoid system is a very important function of human biology. Unfortunately, due to the illegality of cannabis, it is a relatively new field of study. I have read a few articles about Google researching the role of dopamine in learning,…
Cannabijoy
- 171
- 1
- 9
5
votes
1 answer
What could happen if we wrongly assume that the POMDP is an MDP?
Consider the Breakout environment.
We know that the underlying world behaves like an MDP, because, for the evolution of the system, it just needs to know what the current state (i.e. position, speed, and speed direction of the ball, positions of the…
Marco Favorito
- 185
- 7
5
votes
2 answers
What do the neural network's weights represent conceptually?
I understand how neural networks work and have studied their theory well.
My question is: On the whole, is there a clear understanding of how mutation occurs within a neural network from the input layer to the output layer, for both supervised and…
user248884
- 151
- 3