-
As far as I know, initializing weights as zeroes, even as a beginner is highly improper way of initialization. CS231n open lecture [notes](http://cs231n.github.io/neural-networks-2/) says,
> **Pitfal…
-
http://cs231n.stanford.edu/reports/2017/pdfs/200.pdf
1.multi-scale deep network, outperformed most other meth- ods in nearly every metric. Inspection of the output maps, however, shows that the ima…
-
http://idr.openmicroscopy.org/about/
This looks like a very cool collection of microscopy data. Would be very cool to create some basic `TensorGraph` image convolution examples and show how to anal…
-
- https://github.com/revilokeb/vgg16_batchnorm
- https://github.com/HolmesShuan/AlexNet-BN-Caffemodel-on-ImageNet
-
http://arxiv.org/abs/1311.2901
-
### 本周做了
新年第一次周报。
- 写数据库课设，用[EChats](http://echarts.baidu.com)数据可视化，把数据库中的数据，可视化加载了出来，做成了一个炫酷的仪表盘。
- 复习。课设花费的时间太长，有点得不偿失。但觉得是一个不错的练手机会，所以尝试了不少新的功能。
- 看了论文[Deformable Convolutional Networks](ht…
-
Could you please include the script or documentation how this project is converted into HTML?
-
### Module 1: Neural Networks
각 강의 노트마다 번역해주셔야 할 파일은 다음과 같습니다.
- Image Classification: Data-driven Approach, k-Nearest Neighbor, train/val/test splits
- classification.md
- Linear classification: S…
-
We can use CNN to classify more than 10 thousands of images of the ImageNet.
I find that CNN could only classify 10-20 text classes as [this paper](https://arxiv.org/pdf/1502.01710.pdf) write.
So wh…
-
In the [Data Preprocessing](http://cs231n.github.io/neural-networks-2/) section, PCA is described in the following way:
```
# Assume input data matrix X of size [N x D]
X -= np.mean(X, axis = 0) # ze…
ghost updated
7 years ago