Skip to content

[id] cs-229-deep-learning - #154

Open
gitarja wants to merge 5 commits into
shervinea:masterfrom
gitarja:dnn
Open

[id] cs-229-deep-learning#154
gitarja wants to merge 5 commits into
shervinea:masterfrom
gitarja:dnn

Conversation

@gitarja

@gitarja gitarja commented May 29, 2019

Copy link
Copy Markdown
Contributor

No description provided.

@shervinea shervinea added the reviewer wanted Looking for a reviewer label May 30, 2019

@GunawanTri GunawanTri left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Dear Bang Pras.

Ini review saya, Bang. Mohon maaf kemarin belum di-request changes soalnya masih belum paham soal aplikasi ini. Semoga membantu.

Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Modify the translation according to the reviews
Comment thread id/cheatsheet-deep-learning.md
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
Comment thread id/cheatsheet-deep-learning.md Outdated
@gitarja

gitarja commented Nov 2, 2019

Copy link
Copy Markdown
Contributor Author

Mas @GunawanTri bisa cek lagi, saya sudah update

Comment thread id/cheatsheet-deep-learning.md Outdated

**44. 1) We initialize the value:**

⟶Kita menginialisasi value

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Kita menginialisasi value:

Comment thread id/cheatsheet-deep-learning.md Outdated

**19. Dropout ― Dropout is a technique meant at preventing overfitting the training data by dropping out units in a neural network. In practice, neurons are either dropped with probability p or kept with probability 1−p**

⟶Dropout - Dropout adalah sebuah teknik yang digunakan untuk mencegah overfitting pada saraf tiruan dengan men-drop out unit pada sebuah neural network. Pada pengaplikasiannya, neuron di drop dengan probabilitas p atau dipertahankan dengan probabilitas 1-p

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Droput - Dropout adalah sebuah teknik yang digunakan untuk mencegah overfitting pada saraf tiruan dengan memutus unit yang terdapat pada sebuah neural network. Dalam praktiknya, neuron dikurangi dengan probabilitas p atau dipertahankan dengan probabilitas 1-p


**22. Batch normalization ― It is a step of hyperparameter γ,β that normalizes the batch {xi}. By noting μB,σ2B the mean and variance of that we want to correct to the batch, it is done as follows:**

⟶ Normalisasi batch - Normalisasi batch adalah sebuah langkah untuk menormalisasi batch {xi}. Dengan mendefinisikan μB,σ2B sebagai nilai rata-rata dan variansi dari batch yang ingin kita normalisasi, hal tersebut dapat dilakukan dengan cara:

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Normalisasi batch - Normalisasi batch adalah sebuah langkah dari hiperparameter γ,β untuk menormalisasi batch {xi}. Dengan mendefinisikan μB,σ2B sebagai nilai rata-rata dan variansi dari batch yang ingin kita normalisasi, hal tersebut dapat dilakukan dengan cara:

Comment thread id/cheatsheet-deep-learning.md Outdated

**23. It is usually done after a fully connected/convolutional layer and before a non-linearity layer and aims at allowing higher learning rates and reducing the strong dependence on initialization.**

⟶Batch normalisasi biasa ditempatkan setelah sebuah layer fully-connected atau convolutional dan sebelum sebuah non-linear layer yang bertujun untuk memungkinkannya penggunaan nilai learning rate yang lebih tinggi dan mengurangi ketergantungan model pada nilai inisialisasi parameter.

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Normalisasi batch biasa ditempatkan setelah sebuah layer yang sepenuhnya terhubung/konvolusi dan sebelum sebuah layer non-linear yang bertujuan untuk memungkinkannya penggunaan nilai learning rate yang lebih tinggi dan mengurangi ketergantungan kuat pada nilai inisialisasi parameter.

Comment thread id/cheatsheet-deep-learning.md Outdated

**24. Recurrent Neural Networks**

⟶Recurrent Neural Networks

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Recurrent Neural Networks

Comment thread id/cheatsheet-deep-learning.md Outdated

**20. Convolutional Neural Networks**

⟶Convolutional Neural Network

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Convolutional Neural Network

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Gun ini udah gw perbaikin, bisa kita close?

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Bisa Bang kalo udah gak ada tambahan/perbaikan lagi.

@shervinea

Copy link
Copy Markdown
Owner

Thank you @gitarja and @GunawanTri for all your work!

@gitarja: it seems there are a few other unresolved discussions left. Please feel free to let me know whenever you are ready for the merge!

@shervinea shervinea changed the title [id] Deep learning [id] cs-229-deep-learning Oct 6, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

reviewer wanted Looking for a reviewer

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants