Artificial Intelligence
Sponsored by
Sponsored logo
Profile Activity
Network profile
445
reputation
2
12

user8714896

Apparently, this user prefers to keep an air of mystery about them.

0
answers
36
questions
~6k
people reached
  • Member for 1 year, 5 months
  • 85 profile views
  • Last seen Apr 11 at 22:09

Communities (10)

Top network posts

Top tags (68)

Score 0
Posts 9
Posts % 25
Score 0
Posts 9
Score 0
Posts 6
Score 0
Posts 4
Score 0
Posts 3
Score 0
Posts 3
View all tags →

Top posts (36)

All Questions Answers
Votes Newest
9 How does the forget layer of an LSTM work? Dec 23 '19
5 Why is “-0.5 * torch.sum(1 + sigma - mu.pow(2) - sigma.exp())” in Pytorch equivalent to the KL? Feb 13
5 Concrete example of latent variables and observables plugged into the Bayes' rule Nov 21 '19
4 What exactly is a hidden state in an LSTM and RNN? Oct 29 '19
4 Why is the evidence equal to the KL divergence plus the loss? Feb 7 '20
4 Why can't VAE do sequence to sequence name generation? Feb 9 '20
3 Why does this formula $\sigma^2 + \frac{1}{T}\sum_{t=1}^Tf^{\hat{W_t}}(x)^Tf^{\hat{W_t}}(x_t)-E(y)^TE(y)$ approximate the variance? Feb 20
3 Why does every neuron in hidden layers of a multi-layer perceptron typically have the same activation function? [duplicate] Jul 23 '20
3 Why can't LSTMs keep track of the “important parts” of a sequence? Dec 21 '19
3 Why is a softmax used rather than dividing each activation by the sum? Jan 1 '20
View all questions and answers →

Badges (14)

Gold

—

Silver

2

Rarest

Bronze

12

Rarest

View all badges →

Your privacy

By clicking “Accept all cookies”, you agree Stack Exchange can store cookies on your device and disclose information in accordance with our Cookie Policy.