Most Popular
1500 questions
5
votes
2 answers
How could we define passion in artificial intelligence?
Mankind can create machines to do work. How could we define passion in artificial intelligence? How could we define a passionate AI?
Would passion cause the machine to do a better job? How could we compare the performance of a passionate machine, as…
D. Wade
- 541
- 2
- 7
5
votes
1 answer
What effect does batch norm have on the gradient?
Batch norm is a technique where they essentially standardize the activations at each layer, before passing it on to the next layer. Naturally, this will affect the gradient through the network. I have seen the equations that derive the…
information_interchange
- 339
- 1
- 10
5
votes
1 answer
What is the difference between evolutionary computation and evolutionary algorithms?
A book on evolutionary computation by De Jong mentions both the term evolutionary algorithms (EA) as well as evolutionary computation (EC). However, it remains unclear to me what the difference between the two is. According to Vikhar, EA forms a…
dan888
- 91
- 4
5
votes
2 answers
How to calculate the advantage in policy gradient functions?
From my understanding of the REINFORCE policy gradient method, we gently nudge the probabilities of actions based on the advantages. More specifically, the positive advantages increase the probabilities, negative advantages reduce the…
Bob Kimani
- 153
- 6
5
votes
1 answer
Is there any resource that describes in detail a naive example-based machine translation algorithm?
I'm looking to develop a machine translation tool for a constructed language. I think that the example-based approach is the most suitable because the said language is very regular and I can have a sufficient amount of parallel translations.
I…
user34314
5
votes
1 answer
How does the optimization process in hindsight experience replay exactly work?
I was reading the following research paper Hindsight Experience Replay. This is the paper that introduces a concept called Hindsight Experience Replay (HER), which basically attempts to alleviate the infamous sparse reward problem. It is based on…
vikram71198
- 101
- 3
5
votes
3 answers
How to predict time series with accuracy?
I am trying to predict Forex time series. The nature of the market is that 80% of the time the price can not be predicted, but in 20% of the time it can be. For example, if the price drops down very deep, there is 99% probability that there will be…
Nulik
- 151
- 5
5
votes
1 answer
How to replicate legacy systems with machine learning?
Let's suppose that we have a legacy system in which we don't have the source code and this system is on a mainframe written in Cobol. Is there any way using machine learning in which we can learn from the inputs and outputs the way the executables…
jcromanu
- 153
- 3
5
votes
2 answers
What is the purpose of the batch size in neural networks?
Why is a batch size needed to update the weights of a neural network?
According to that Youtube Video from 3B1B, the weights are updated by calculating the error between expectation and outcome of the neural net. Based on that, the chain rule is…
MScott
- 445
- 4
- 13
5
votes
1 answer
Many of the best probabilistic models represent probability distributions only implicitly
I am currently studying Deep Learning by Goodfellow, Bengio, and Courville. In chapter 5.1.2 The Performance Measure, P, the authors say the following:
The choice of performance measure may seem straightforward and objective, but it is often…
The Pointer
- 569
- 3
- 19
5
votes
1 answer
What AI applications exist to solve sustainability issues?
The Sustainable Development Goals of the United Nations describe a normative framework which states what future development until 2030 should strive for. On a more abstract level a basic definition describes sustainable development as
development…
cknoll
- 161
- 3
5
votes
1 answer
How to detect vanishing gradients?
Can vanishing gradients be detected by the change in distribution (or lack thereof) of my convolution's kernel weights throughout the training epochs? And if so how?
For example, if only 25% of my kernel's weights ever change throughout the epochs,…
Elegant Code
- 153
- 1
- 7
5
votes
1 answer
How to define an action space when an agent can take multiple sub-actions in a step?
I'm attempting to design an action space in OpenAI's gym and hitting the following roadblock. I've looked at this post which is closely related but subtly different.
The environment I'm writing needs to allow an agent to make between $1$ and $n$…
Seyed Moein Ayyoubzadeh
- 130
- 8
5
votes
1 answer
Why not more TD() in actor-critic algorithms?
Is there either an empirical or theoretical reason that actor-critic algorithms with eligibility traces have not been more fully explored? I was hoping to find a paper or implementation or both for continuous tasks (not episodic) in continuous…
Nick Kunz
- 145
- 1
- 5
5
votes
1 answer
Is there a reason to use TensorFlow over PyTorch for research purposes?
I've been using PyTorch to do research for a while and it seems to be quite easy to implement new things with. Also, it is easy to learn and I didn't have any problem with following other researchers code so far.
However, I wonder whether…
SpiderRico
- 990
- 9
- 18