Stack Overflow
Stack Overflow

Questions tagged [edward]

Edward is a Python library for probabilistic modeling, inference, and criticism, built on TensorFlow.

Edward is a Python library for probabilistic modeling, inference, and criticism, built on TensorFlow. It is a testbed for fast experimentation and research with probabilistic models, ranging from classical hierarchical models on small data sets to complex deep probabilistic models on large data sets. Edward fuses three fields: Bayesian statistics and machine learning, deep learning, and probabilistic programming.

Website: http://edwardlib.org/

Source code: https://github.com/blei-lab/edward

24 questions
0
votes
0 answers

Reconstruct dropout rate for edward2's DenseVariationalDropout layer

I am currently training a neural network based on simulated data. The standard architecture of the model is as follows: Input layer (5 features) Dense hidden layer (64 units) Dense hidden layer (32 units) Dense output layer (2 units) To improve…
Lutz Köhler
  • 1
  • 2
0
votes
0 answers

can't install edward2 a library in python

I want to install edward2 library: https://github.com/google/edward2. I used this command: pip install "git+https://github.com/google/edward2.git#egg=edward2". But when I want to import it in spyder it had an error: ModuleNotFoundError: No module…
user12682643
0
votes
2 answers

predicting p of binomial with beta prior in edward2 & tensorflow2

The following code predicts the p of the binomial distribution by using beta as prior. Somehow, sometimes, I get meaningless results (acceptance rate = 0). When I write the same logic with pymc3, I have no issue. I couldn't see what I am missing…
ndemir
  • 1,881
  • 3
  • 19
  • 25
0
votes
1 answer

Edward2 implementation of Edward's HMC method

Edward1 contained a method HMC with with the following syntax: inference = ed.HMC({z: qz}) inference.run() I'm having difficulty tracking down the migration for this. Neither Edward2 nor TPF contain this package. When looking up the migration…
user10614851
0
votes
1 answer

Can not use Edward 1.3.5 with Tensorflow 1.14.0

I am trying to use Edward library for deploying a PPCA model and facing difficulties while installing it on windows. I successfully installed Edward 1.3.5 using (pip install edward ) and tensorflow 1.14.0 using (pip install tensorflow) but when I…
Rahul Deshmukh
  • 1
0
votes
1 answer

How do I translate this Edward code to TFP code?

I have coded a Probabilistic Matrix Factorization model in Edward. I am trying to port it over to TFP, but I am not sure how to define the log-likelihood and KL divergence terms. Here is the code in Edward - # MODEL U = Normal( loc=0.0, …
modin3956
  • 149
  • 2
  • 11
0
votes
1 answer

L2 regularization of weights in Edward

I'm trying to understand how can we use the regularization with Edward models. I'm still new to tensorflow (which is used as the backend of the Edward). Consider the model below, # prior w=Normal(loc=tf.zeros((d,c)),scale=tf.ones((d,c))) #…
Nadheesh
  • 23
  • 5
0
votes
1 answer

Incompatible shapes error in bayesian neural network

I am a new in machine learning. I have a project about bayesian neural network to predict football result. Then I follow instruction from this link. Then I make code like this: import sys from math import floor import edward as ed import numpy as…
beginner
  • 41
  • 5
0
votes
1 answer

Could someone explain more clear "programming" part of probabilistic programming?

Usually in the docs for probabilistic programming frameworks I can read much about MCMC but not very much about programming. Every example I see have usually only very short and simple probabilistic program. Usually they are about 5-10 lines of…
RedRus
  • 118
  • 6
1
2