TheCG's user avatar
TheCG's user avatar
TheCG's user avatar
TheCG
  • Member for 4 years, 10 months
  • Last seen this week
  • France
6 votes
Accepted

What is the benefit of latent variables?

3 votes

Examples of state space models where the filtering problem can be solved analytically

3 votes
Accepted

What happens if the observations are connected in a hidden Markov model (HMM)?

3 votes

Feature selection using Restricted Boltzmann Machine

3 votes

Replicating an experiment on GMRF (Gaussian Markov Random Field)

3 votes

Hidden Markov Model: How to define the state observation matrix B for continuous (Normal) observations?

3 votes
Accepted

Graphic model factorizing, marginalization

3 votes

Are Hidden Markov Models the right tool for signal segmentation task?

3 votes
Accepted

Do variational approximations capture the flow of influence or "conditional independence" relationships in graphical models?

3 votes

Replacing the KL-divergence term in a VAE with parameter regularization

2 votes

Why do we use the same parameters for the joint, marginal and conditional distributions in VAEs?

2 votes
Accepted

Introduction to approximate message passing

2 votes
Accepted

Interpreting viterbi decoding and posterior probabilities

2 votes

Factor graph equivalent to Markov networks

2 votes
Accepted

Hidden Markov Models and How to Interpret Probability of the Overall Sequence?

2 votes
Accepted

Doubt on d-separation

2 votes
Accepted

How do you find the most probable state path given an observed sequence with infinite emissions values in MATLAB?

2 votes

Examples of applications of Markov random fields to data with a small number of variables

2 votes
Accepted

What step do they take to solve the limiting distribution

1 vote

Why can a Restricted Boltzmann Machine reconstruct using same weights?

1 vote

Why are the additional set of parameters in discriminative models necessary(in Minka's 2005 paper)?

1 vote
Accepted

Seeing a tree graphical model as a Markov model

1 vote
Accepted

Number of Variables Needed to Represent Bayesian Network and Independence

1 vote
Accepted

Calculating Probabilities in a Bayesian Network

1 vote
Accepted

Disconnected components in graphical models

1 vote
Accepted

Deriving reward functions in Sutton & Barto

1 vote

How to verify if a graphical model has the markov property?

1 vote

Does VAE backprop start from the decoder all the way to encoder?

1 vote
Accepted

Is there any work on, given a set of conditional independences, build the graphical model?

1 vote

VAE: what activation function (if any) to use for the last layer of my decoder if I don't want to assume any knowledge about the scale of my inputs?