Skip to main content

Questions tagged [generator]

The tag has no usage guidance.

Filter by
Sorted by
Tagged with
0 votes
0 answers
17 views

How to train with convLSTM2D on variable input shape?

I am classifying time series of 72x72 images in 4 filters (just like RGB). Things work well ...
user43280's user avatar
  • 101
0 votes
0 answers
27 views

How to improve the expressibility of a cGAN

I am training a cGAN on the problem of reconstructing a density matrix. My inputs to the network are matrices and expectation values. That is, I have a set $(A,x)$ where A are measurement operators, ...
Dimitri's user avatar
  • 15
1 vote
1 answer
139 views

Markov chain: inferring transition rates from equilibrium

I feel like I have been having a very dumb week trying to solve/research this problem and that I am missing an easy solution or that it is not possible. Given an equilibrium distribution (say from a ...
markovian's user avatar
1 vote
0 answers
26 views

Pre-training on a subset and after train again with whole

I am implementing a Context Encoder on CelebA dataset, due my hardware limitation the whole dataset takes too long for training the Generator and Discriminator, Can I pre-training my models on a ...
Nexkira's user avatar
  • 11
0 votes
0 answers
19 views

Continuous Time Markov chain [duplicate]

What is the intuition behind 'Infinitesimal generator matrix?What why we need it?Why it is called generator matrix?what it generates?
Jamil Chowdhury's user avatar
2 votes
2 answers
699 views

Is combining ReLU with Tanh a good idea?

I am reading Kupyn, O., Martyniuk, T., Wu, J., & Wang, Z. (2019). DeblurGAN-v2: Deblurring (Orders-of-Magnitude) Faster and Better. [PDF]. I have a CNN implementation for the Generator of a GAN. ...
ElPapi42's user avatar
  • 119
2 votes
1 answer
36 views

Different signal length for each batch

I wonder if it Is it possible to have a different signal length for each batch when training a model. Batch 1 : all signals of length 1000 Batch 2 : all signals of length 2000 Batch 3 : all signals ...
bjornsing's user avatar
  • 209
0 votes
1 answer
497 views

Random number generator independence

I have a naïve question about random number generators. Say I want to generate a set of random variables from different exponential distributions,$$X_i \sim \mathcal {Exp}(\lambda_i)$$ Assume the$X_i$'...
Jeffrey's user avatar
  • 107
4 votes
1 answer
1k views

Questions regarding generator function of a copula

Context This post concerns Archimedean copulas, specifically as given in [1]. In this post, I ask a series of questions with the intent of clarifying what is written in [1]. Questions In [1], it ...
Michael Levy's user avatar
2 votes
0 answers
254 views

Interpolating time ordered smooth function into space

I am using GAMs in R to generate daily weather variables, mainly precipitation and temperature. Currently, I am fitting a model for each weather station but I would like to use it in places where ...
Alessio Bocco's user avatar
1 vote
0 answers
137 views

How to generate a Bernoulli distribution based on a given Bernoulli distribution? [closed]

We have a Bernoulli distribution which outputs 1 with probability C and outputs 0 with probability 1-C. C is unknown. Now we would like to generate a new Bernoulli distribution that outputs 1 with ...
HoiM's user avatar
  • 11
4 votes
0 answers
470 views

Advantage of fit_generator() in keras [closed]

I was wondering if the fit_generator() in keras has any advantage in respect to memory usage over using the usual fit() method ...
V1nc3nt's user avatar
  • 405
2 votes
2 answers
55 views

Generates variates of $F^s$ given a known algorithm for variates of $F$

Let rv $X$ have a distribution $F (t):={\rm Prob}(X <t)$ and rv $Y$ have a distribution $G (t):=(F(t))^s$ for some constant $s>0$. Suppose that I know an algorithm for generating random variates ...
rytis's user avatar
  • 121
13 votes
3 answers
19k views

Why use Binary Cross Entropy for Generator in Adversarial Networks

I'm trying to work with General Adversarial Networks and there's something I'm seeing everywhere but can't explain why... the GANs are usually constructed from a Generator (which usually generates an ...
Cypher's user avatar
  • 515
0 votes
1 answer
104 views

Data set generator [closed]

I'd like to ask if someone knows a good data set generator for multi-target/Multivariate regression All the best Richard
RichardSutherland's user avatar
0 votes
1 answer
169 views

Markov Process-Variance of time until jump

A Markov process on E = {1, 2} is constructed according to holding time parameters λ1 = 2 and λ2 = 4; the defining Markov chain has transition probabilities p11 = p12 = 0.5 and p21 = 1. How do I ...
kullapparos's user avatar
3 votes
0 answers
281 views

Discrete time generator of stochastic process

While looking at one paper about Metropolic Hasting optimal convergence rates, I came accross a discrete time generator of Markov chain. It is defined as follows: $$G V(x)=nE\left [ \left( V(y)-V(x)\...
Tomas's user avatar
  • 1,243