SHY

Marathon. Food. Programming.


  • 首頁

  • 歸檔

  • 標籤

原味戚風蛋糕 Original Chiffon Cake

發表於 2020-04-30

材料 Materials

  • 蛋 4 顆(4 eggs)
  • 油 55g(55g oil)
  • 低筋麵粉 73g(73g pastry flour)
  • 牛奶 55g(55g milk)
  • 醋 7g(7g vinegar)
  • 糖 55g(55g sugar)

這樣的份量是一個 6 英吋中空圓形烤模。參考資料影片為 7 寸中空模。

閱讀全文 »

Run Less Run Faster

發表於 2019-08-08

3 + 2 Training

3 - Three quality runs

Track repeats

Tempo

Long

  • repeat: overload - fatigue - recovery - adaption
  • overload means: father, faster, more often. Overload ONLY ONE variable at a time.

2 - Two cross training

Notes

  • Consistency is the key to fitness.
  • Ideal racing temperatures: 40 to 60 degrees Fahrenheit.(5 to 16 degrees Celsius.)
  • If degree is above 60F, -1sec/mile/degree(F).

CS230 Deep Learning

發表於 2018-10-10

We use www.menti.com to communicate with teacher

Steps of ML application

1. Select problem

2. Get data

How long do you spend on collecting data?

It’s recommend that quickly collect data at the firt time as we start the project, so we can modify the design of the model or collect more data by training the model.

Keep clear notes on reperlment line(?).

How would you collecting data?

3. Design model

4. Train model

5. Test model

6. Deploy

Edge devices
audio —> NN —-> 0/1
but their might be large NN, it waste times.

audio —> VAD —> NN —> 0/1
VAD is checking if the voice actually detective.

option 1 will be more simpler and faster to option 2. It maybe have many errors or noises in the result of option 1, but the following large NN will take care of it, we don’t have to worry about it.


In this case, option 2 will be a proper choice for Non-ML just detect for loud or seilence, it can not distinguish the anscent.

7. Maintain

閱讀全文 »

TOEFL in Biology

發表於 2018-09-27

Kingdom 界

Animalia, Plantae, Fungi, Bacteria

閱讀全文 »

Optimize Backpropagation of Cost Function in Neural Network (CS229)

發表於 2018-07-22

Idea of backpropagation


(source: https://www.coursera.org/learn/machine-learning/)

閱讀全文 »

Backpropagation Intuition of Neural Network (CS229)

發表於 2018-07-21

Recall cost function

$$J(\Theta)=-\frac{1}{m}\left[\sum_{i=1}^m\sum_{k=1}^Ky_k^{(i)}\log\left(h_{\Theta}(x^{(i)})\right)_k+(1-y_k^{(i)})\log\left(1-h_{\theta}(x^{(i)})_k\right)\right]+\frac{\lambda}{2m}\sum_{l=1}^{L-1}\sum_{i=1}^{s_l}\sum_{j=1}^{s_l+1}\left(\Theta_{ji}^{(l)}\right)^2\tag{1}$$

閱讀全文 »

Backpropagation Algorithm for Minimize Cost Function (CS229)

發表於 2018-07-21

Recall cost function in neural network

$$J(\Theta)=-\frac{1}{m}\left[\sum_{i=1}^m\sum_{k=1}^Ky_k^{(i)}\log\left(h_{\Theta}(x^{(i)})\right)_k+(1-y_k^{(i)})\log\left(1-h_{\theta}(x^{(i)})_k\right)\right]+\frac{\lambda}{2m}\sum_{l=1}^{L-1}\sum_{i=1}^{s_l}\sum_{j=1}^{s_l+1}\left(\Theta_{ji}^{(l)}\right)^2$$

閱讀全文 »

Cost Function in Neural Network (CS229)

發表於 2018-07-21

Notations

$(x^{(1)},y^{(1)}),(x^{(2)},y^{(2)}),…,(x^{(m)},y^{(m)})$

$m$ training sets.

閱讀全文 »

Examples of Neural Network (CS229)

發表於 2018-07-18

Non-linear classification example

XOR / XNOR function

閱讀全文 »

Neural Network (CS229)

發表於 2018-07-17

Origins

Algorithms that try to mimic the brain.

閱讀全文 »
12…5
Shuhan Yu

Shuhan Yu

https://github.com/ShuHanYu

45 文章
109 標籤
© 2020 Shuhan Yu
由 Hexo 強力驅動
主題 - NexT.Muse