user avatar
user avatar
user avatar
Indie AI
  • Member for 6 years, 9 months
  • Last seen more than 5 years ago
172 votes
Accepted

What does 1x1 convolution mean in a neural network?

82 votes
Accepted

What is an embedding layer in a neural network?

78 votes
Accepted

Understanding "almost all local minimum have very similar function value to the global optimum"

52 votes

Neural network with skip-layer connections

44 votes
Accepted

Adam optimizer with exponential decay

42 votes

Pre-training in deep convolutional neural network?

25 votes

How to initialize the elements of the filter matrix?

14 votes
Accepted

Rules for selecting convolutional neural network hyperparameters

12 votes

How much data for deep learning?

11 votes
Accepted

Why is the softmax used to represent a probability distribution?

10 votes
Accepted

Does number of layers in neural network corresponds to degree of the approximation function?

9 votes
Accepted

How to understand the geometric intuition of the inner workings of neural networks?

8 votes

Input Normalisation for ReLU neurons

8 votes
Accepted

Why does SGD and back propagation work with ReLUs?

7 votes

Tips for training dropout neural network

6 votes
Accepted

How to know where to put bias terms in neural nets?

6 votes
Accepted

What's the difference between convolutional neural network and convolutional auto encoders?

6 votes

Python Lasagne tutorial: validation error lower than training error

5 votes
Accepted

Dealing with small batch size in SGD training

4 votes
Accepted

how do you handle a "none of these" class in a CNN

4 votes

Deep learning: representation learning or classification?

4 votes
Accepted

Feature standardization for convolutional network on sparse data

3 votes

My ReLU network fails to launch

3 votes
Accepted

Is finding a good multilayer perceptron (MLP) model just luck?

3 votes

Why do we use non linearities in artificial neural networks (ANNs) and convolutional neural networks (CNNs)?

2 votes

The bottleneck of applying deep learning in practice

2 votes

Sensitivity of DNN-based classifiers to centering and orientation of object in images

2 votes

Deep learning - unsupervised vs. supervised shape recognition

2 votes
Accepted

ZCA-Whitening on ImageNet sized dataset

2 votes

What loss function should I use for binary detection in face/non-face detection in CNN?