-
Hi, I am getting the following error when running the mnist example via fpm
```
$ fpm run --example mnist --profile debug --compiler ifort
mod_constants.f90 done.
mod_random…
ofmla updated
1 month ago
-
### 정규 방정식을 이용한 선형 회귀
```python
import numpy as np
X = 2 * np.random.rand(100, 1) # 0과 1 사이의 uniform distribution random 값 생성
y = 4 + 3 * X + np.random.randn(100, 1) # 평균 0, 표준편차 1인 gaussian di…
i-zro updated
4 years ago
-
Hi guys,
Really appreciate your elegent code!
Right now I playing with the batch size setting. For Mnist dataset, when I set the batch size = 1, I will get nan for the weight. I guess that is be…
-
I did not quite understand the tasks and meta mechanism used in the paper, with the replies of the author, I got a clearer view. The conclusion and discussion will be listed below to help more people.…
-
For a graph based library, the internal nodes should probably be written in a better language than Python.
As a result the performance isn't comparable to similar solutions in c++ when it could be.
-
1.How to calculate the global optimum p ∗ in the relative suboptimality plots and regret plots?
2.During your model training, do you use training data mini-batch or one by one?
-
### Idea Title
Stochastic Gradient Descent (SGD)
### Idea Description
Stochastic Gradient Descent updates the model's parameters by calculating the gradient of the loss function for a single train…
-
http://arxiv.org/pdf/1502.03167v3.pdf
Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previou…
leo-p updated
7 years ago
-
Memory allocations and release will probably become a bottleneck during the forward and backward propagation.
During the forward pass it will hold inputs tensor in cache. During backward pass it wi…
-
I am working on a project where I sample a set of n-dimensional points from a Gaussian distribution (of learnt parameters) as follows and then evaluate those points based on a loss function to update …