「Courseraに日本語字幕をつけよう！/現在のステータス」の編集履歴（バックアップ）一覧はこちら
追加された行は緑色になります。
削除された行は赤色になります。
現在は機械学習のコースを和訳中です。
和訳結果はこちら（login required) https://share.coursera.org/wiki/index.php/ML:Subtitles
----
Week7
Using An SVM (21 min)
今回終わった物
Mathematics Behind Large Margin Classification (Optional) (20 min)
Kernels I (16 min)
Kernels II (16 min)
前回終わってる物
Optimization Objective (15 min)
Large Margin Intuition (11 min)
-----
Week 6
今回終わった物
Deciding What to Do Next Revisited (7 min)
Prioritizing What to Work On (10 min)
Error Analysis (13 min)
Error Metrics for Skewed Classes (12 min)
Trading Off Precision and Recall (14 min)
Data For Machine Learning (11 min)
既に終わってる物
Learning Curves (12 min)
Completed Deciding What to Try Next (6 min)
Completed Evaluating a Hypothesis (8 min)
Completed Model Selection and Train/Validation/Test Sets (12 min)
Diagnosing Bias vs. Variance (8 min)
Regularization and Bias/Variance (11 min)
後半最大の山場も終わり！
----
Week5
今回終わった物
Gradient Checking (12 min)
Random Initialization (7 min)
Putting It Together (14 min)
Autonomous Driving (7 min)
前回終わってる物
Cost Function (7 min)
Backpropagation Algorithm (12 min)
Backpropagation Intuition (13 min)
Implementation Note: Unrolling Parameters (8 min)
Week5も終わり！で前半も終わりです。
----
Week4
今回終わった物
Examples and Intuitions I (7 min)
Examples and Intuitions II (10 min)
Multiclass Classification (4 min)
前回終わってる物
Non-linear Hypotheses (10 min)
Neurons and the Brain (8 min)
Model Representation I (12 min)
Model Representation II (12 min)
-----
Week 3
今回終わった物
Multiclass Classification: One-vs-all (6 min)
The Problem of Overfitting (10 min)
Cost Function (10 min)
Regularized Linear Regression (11 min)
Regularized Logistic Regression (9 min)
前回終わってる物
Classification (8 min)
Hypothesis Representation (7 min)
Decision Boundary (15 min)
Cost Function (11 min)
Simplified Cost Function and Gradient Descent (10 min)
Advanced Optimization (14 min)
Week3も終わった！
----
Week 1, 2
今回終わった物
-Features and Polynomial Regression (8 min)
-Normal Equation (16 min)
- Normal Equation Noninvertibility (Optional) (6 min)
前回終わった物
- Inverse and Transpose (11 min)
-Gradient Descent For Linear Regression (10 min)
-Descent in Practice II - Learning Rate (9 min)
Week1, 2も終わり！
----
Summary and Thank You (5 min)
Week10
今回終わった物
Sliding Windows (15 min)
Getting Lots of Data and Artificial Data (16 min)
Ceiling Analysis: What Part of the Pipeline to Work on Next (14 min)
前回までに終わった物
Learning With Large Datasets (6 min)
Stochastic Gradient Descent (13 min)
Mini-Batch Gradient Descent (6 min)
Stochastic Gradient Descent Convergence (12 min)
Online Learning (13 min)
Map Reduce and Data Parallelism (14 min)
Problem Description and Pipeline (7 min)
Week10終わった！やった！
----
以下は2周目の実績
Week10
Sliding Windows (15 min)
Getting Lots of Data and Artificial Data (16 min)
Ceiling Analysis: What Part of the Pipeline to Work on Next (14 min)
Summary and Thank You (5 min)
今回終わった物
Learning With Large Datasets (6 min)
Stochastic Gradient Descent (13 min)
Mini-Batch Gradient Descent (6 min)
Stochastic Gradient Descent Convergence (12 min)
Online Learning (13 min)
Map Reduce and Data Parallelism (14 min)
Problem Description and Pipeline (7 min)
----
Week9
Multivariate Gaussian Distribution (Optional) (14 min)
Anomaly Detection using the Multivariate Gaussian Distribution (Optional) (14 min)
今回終わった物
Content Based Recommendations (15 min)
Collaborative Filtering (10 min)
Collaborative Filtering Algorithm (9 min)
Vectorization: Low Rank Matrix Factorization (8 min)
Implementational Detail: Mean Normalization (9 min)
前回終わってる物
Problem Motivation (8 min)
Gaussian Distribution (10 min)
Algorithm (12 min)
Developing and Evaluating an Anomaly Detection System (13 min)
Anomaly Detection vs. Supervised Learning (8 min)
Choosing What Features to Use (12 min)
Problem Formulation (8 min)
-----
Week8
Choosing the Number of Principal Components (11 min)
Reconstruction from Compressed Representation (4 min)
Advice for Applying PCA (13 min)
後から終えた物
Choosing the Number of Clusters (8 min)
Motivation I: Data Compression (10 min)
Motivation II: Visualization (6 min)
Principal Component Analysis Problem Formulation (9 min)
Principal Component Analysis Algorithm (15 min)
今回終わった物
Optimization Objective (7 min)
Random Initialization (8 min)
前回終わってる物
Unsupervised Learning: Introduction (3 min)
K-Means Algorithm (13 min)
----
Week7
Mathematics Behind Large Margin Classification (Optional) (20 min)
Kernels I (16 min)
Kernels II (16 min)
Using An SVM (21 min)
前回終わってる物
Optimization Objective (15 min)
Large Margin Intuition (11 min)
この週はスキップ。
----
Week 6
Deciding What to Do Next Revisited (7 min)
Prioritizing What to Work On (10 min)
Error Analysis (13 min)
Error Metrics for Skewed Classes (12 min)
Trading Off Precision and Recall (14 min)
Data For Machine Learning (11 min)
今回終わった物
Learning Curves (12 min)
前回終わってる物
Completed Deciding What to Try Next (6 min)
Completed Evaluating a Hypothesis (8 min)
Completed Model Selection and Train/Validation/Test Sets (12 min)
Diagnosing Bias vs. Variance (8 min)
Regularization and Bias/Variance (11 min)
----
Week5
Gradient Checking (12 min)
Random Initialization (7 min)
Putting It Together (14 min)
Autonomous Driving (7 min)
done
Implementation Note: Unrolling Parameters (8 min)
前回終わってる物
Cost Function (7 min)
Backpropagation Algorithm (12 min)
Backpropagation Intuition (13 min)
今週は一本。もう一本くらいやりたかったけど、年末は仕方ないかなぁ。
-----
Week4
Examples and Intuitions I (7 min)
Examples and Intuitions II (10 min)
Multiclass Classification (4 min)
done
Model Representation II (12 min)
前回終わってる物
Non-linear Hypotheses (10 min)
Neurons and the Brain (8 min)
Model Representation I (12 min)
今週は私的な事情で進みが悪かったです。それでも一本終えたので残り三つ。
-----
Week 3
Multiclass Classification: One-vs-all (6 min)
The Problem of Overfitting (10 min)
Cost Function (10 min)
Regularized Linear Regression (11 min)
Regularized Logistic Regression (9 min)
done
Cost Function (11 min)
Simplified Cost Function and Gradient Descent (10 min)
Advanced Optimization (14 min)
前回終わってる物
Classification (8 min)
Hypothesis Representation (7 min)
Decision Boundary (15 min)
5本残ったけどもともとWeek3は前回たくさん残ってた週の一つなので、良く健闘したかなぁ。
一応前回訳した分と合わせると半分は超えた（6/11）
-----
Week 1, 2
-Features and Polynomial Regression (8 min)
-Normal Equation (16 min)
- Normal Equation Noninvertibility (Optional) (6 min)
今回終わった物
- Inverse and Transpose (11 min)
-Gradient Descent For Linear Regression (10 min)
-Descent in Practice II - Learning Rate (9 min)
3つ残りましたが、もうあと一歩ですね。
最初の週は線形代数の補講が大量にあるので大変でした。
----
以下は前回。
----
こっそりメモ。
終わった物
Algorithm (12 min)
Developing and Evaluating an Anomaly Detection System (13 min)
Choosing What Features to Use (12 min)
Problem Formulation (8 min)
----
2013年4月から、機械学習のコースを翻訳していきます。
ここには各週のステータスを書いていきます。
2013年6月4週
今週は2週間分一気にアップされたので膨大です。
Algorithm (12 min) *
Developing and Evaluating an Anomaly Detection System (13 min)
Anomaly Detection vs. Supervised Learning (8 min)
Choosing What Features to Use (12 min)
Multivariate Gaussian Distribution (Optional) (14 min)
Anomaly Detection using the Multivariate Gaussian Distribution (Optional) (14 min)
Problem Formulation (8 min)
Content Based Recommendations (15 min)
Collaborative Filtering (10 min)
Collaborative Filtering Algorithm (9 min)
Vectorization: Low Rank Matrix Factorization (8 min)
Implementational Detail: Mean Normalization (9 min)
Learning With Large Datasets (6 min)
Stochastic Gradient Descent (13 min)
Mini-Batch Gradient Descent (6 min)
Stochastic Gradient Descent Convergence (12 min)
Online Learning (13 min)
Map Reduce and Data Parallelism (14 min)
Problem Description and Pipeline (7 min)
Sliding Windows (15 min)
Getting Lots of Data and Artificial Data (16 min)
終わった物
Problem Motivation (8 min)
Gaussian Distribution (10 min)
----
2013年6月3週
今週は別件で時間を食われたので少しさぼり。
Optimization Objective (7 min)
Random Initialization (8 min)
Choosing the Number of Clusters (8 min)
Motivation I: Data Compression (10 min)
Motivation II: Visualization (6 min)
Principal Component Analysis Problem Formulation (9 min)
Principal Component Analysis Algorithm (15 min)
Choosing the Number of Principal Components (11 min)
Reconstruction from Compressed Representation (4 min)
Advice for Applying PCA (13 min)
終わった物
Unsupervised Learning: Introduction (3 min)
K-Means Algorithm (13 min)
----
2013年6月2週
今週は結構作業はしたのですが、英文の数が多くてあまり進みませんでした。
早口だったんでしょうかね？
Mathematics Behind Large Margin Classification (Optional) (20 min)
Kernels I (16 min)
Kernels II (16 min)
Using An SVM (21 min)
終わった物
Optimization Objective (15 min)
Large Margin Intuition (11 min)
----
2013年6月1週
今週は5動画も訳せたのですが、動画の数が多いので全体から見ると
5/12
でした。
Learning Curves (12 min)
Deciding What to Do Next Revisited (7 min)
Prioritizing What to Work On (10 min)
Error Analysis (13 min)
Error Metrics for Skewed Classes (12 min)
Trading Off Precision and Recall (14 min)
Data For Machine Learning (11 min)
終わった物
Completed Deciding What to Try Next (6 min)
Completed Evaluating a Hypothesis (8 min)
Completed Model Selection and Train/Validation/Test Sets (12 min)
Diagnosing Bias vs. Variance (8 min)
Regularization and Bias/Variance (11 min)
----
2013年5月4週
数としては3/8ですが、Unroll、Gradient Checking、Random Initialization、Autonomous Drivingは補講のような物なので、見た目よりは量こなせているかなぁ、と思います。
Completed Implementation Note: Unrolling Parameters (8 min)
Completed Gradient Checking (12 min)
Random Initialization (7 min)
Putting It Together (14 min)
Autonomous Driving (7 min)
終わった物
Completed Cost Function (7 min)
Completed Backpropagation Algorithm (12 min)
Completed Backpropagation Intuition (13 min)
----
2013年5月3週
3/7動画終わりました。
量的には半分に届いてませんが、Multiclass Classificationは短い動画なので実際は半分くらいは終わってます。
当面は半分を目標にやっていこうかな、と思いはじめています。
Model Representation II (12 min)
Examples and Intuitions I (7 min)
Examples and Intuitions II (10 min)
Multiclass Classification (4 min)
終わった物
Non-linear Hypotheses (10 min)
Neurons and the Brain (8 min)
Model Representation I (12 min)
----
2013年5月2週
3/11動画訳しました。
8動画も残ったけど、一週間に11動画はちょっと予想外でした。
二週間と勘違いしてた(^_^;)
後半は結構悪くないペースだったんですが、序盤に先週分の後始末が多かったのが敗因か。
今週はかなり手伝ってもらえました。感謝。
Cost Function (11 min)
Simplified Cost Function and Gradient Descent (10 min)
Advanced Optimization (14 min)
Multiclass Classification: One-vs-all (6 min)
The Problem of Overfitting (10 min)
Cost Function (10 min)
Regularized Linear Regression (11 min)
Regularized Logistic Regression (9 min)
終わった物
Classification (8 min)
Hypothesis Representation (7 min)
Decision Boundary (15 min)
----
2つほど作業中ですが、それらが終わるとすると6動画ほど残りました。
ちょっと私用が忙しかったので(^_^;)
----
今週はOptionalな物以外からやっていきます。
2013年4月4週
現在作業中の物には「＊」をつけておきます。
-Gradient Descent For Linear Regression (10 min)
-Descent in Practice II - Learning Rate (9 min)
-Features and Polynomial Regression (8 min)
-Normal Equation (16 min)
- Normal Equation Noninvertibility (Optional) (6 min)
Optionalな物
- Inverse and Transpose (11 min)
反映待ちな物
- Multiple Features (8 min)
- Matrix Vector Multiplication (14 min)
- Matrix Matrix Multiplication (11 min)
-Matrix Multiplication Properties (9 min)
- Gradient Descent in Practice I - Feature Scaling (9 min)
-What's Next (6 min)
- Gradient Descent for Multiple Variables (5 min)
現在は機械学習のコースを和訳中です。
和訳結果はこちら（login required) https://share.coursera.org/wiki/index.php/ML:Subtitles
-----
Week8
Choosing the Number of Principal Components (11 min)
Reconstruction from Compressed Representation (4 min)
Advice for Applying PCA (13 min)
前回までに終わってる物
Unsupervised Learning: Introduction (3 min)
K-Means Algorithm (13 min)
Optimization Objective (7 min)
Random Initialization (8 min)
Choosing the Number of Clusters (8 min)
Motivation I: Data Compression (10 min)
Motivation II: Visualization (6 min)
Principal Component Analysis Problem Formulation (9 min)
Principal Component Analysis Algorithm (15 min)
----
Week7
今回終わった物
Mathematics Behind Large Margin Classification (Optional) (20 min)
Kernels I (16 min)
Kernels II (16 min)
Using An SVM (21 min)
前回終わってる物
Optimization Objective (15 min)
Large Margin Intuition (11 min)
Week7も終わった！後半戦もあとは消化試合みたいなのを残すのみ！
-----
Week 6
今回終わった物
Deciding What to Do Next Revisited (7 min)
Prioritizing What to Work On (10 min)
Error Analysis (13 min)
Error Metrics for Skewed Classes (12 min)
Trading Off Precision and Recall (14 min)
Data For Machine Learning (11 min)
既に終わってる物
Learning Curves (12 min)
Completed Deciding What to Try Next (6 min)
Completed Evaluating a Hypothesis (8 min)
Completed Model Selection and Train/Validation/Test Sets (12 min)
Diagnosing Bias vs. Variance (8 min)
Regularization and Bias/Variance (11 min)
後半最大の山場も終わり！
----
Week5
今回終わった物
Gradient Checking (12 min)
Random Initialization (7 min)
Putting It Together (14 min)
Autonomous Driving (7 min)
前回終わってる物
Cost Function (7 min)
Backpropagation Algorithm (12 min)
Backpropagation Intuition (13 min)
Implementation Note: Unrolling Parameters (8 min)
Week5も終わり！で前半も終わりです。
----
Week4
今回終わった物
Examples and Intuitions I (7 min)
Examples and Intuitions II (10 min)
Multiclass Classification (4 min)
前回終わってる物
Non-linear Hypotheses (10 min)
Neurons and the Brain (8 min)
Model Representation I (12 min)
Model Representation II (12 min)
-----
Week 3
今回終わった物
Multiclass Classification: One-vs-all (6 min)
The Problem of Overfitting (10 min)
Cost Function (10 min)
Regularized Linear Regression (11 min)
Regularized Logistic Regression (9 min)
前回終わってる物
Classification (8 min)
Hypothesis Representation (7 min)
Decision Boundary (15 min)
Cost Function (11 min)
Simplified Cost Function and Gradient Descent (10 min)
Advanced Optimization (14 min)
Week3も終わった！
----
Week 1, 2
今回終わった物
-Features and Polynomial Regression (8 min)
-Normal Equation (16 min)
- Normal Equation Noninvertibility (Optional) (6 min)
前回終わった物
- Inverse and Transpose (11 min)
-Gradient Descent For Linear Regression (10 min)
-Descent in Practice II - Learning Rate (9 min)
Week1, 2も終わり！
----
Summary and Thank You (5 min)
Week10
今回終わった物
Sliding Windows (15 min)
Getting Lots of Data and Artificial Data (16 min)
Ceiling Analysis: What Part of the Pipeline to Work on Next (14 min)
前回までに終わった物
Learning With Large Datasets (6 min)
Stochastic Gradient Descent (13 min)
Mini-Batch Gradient Descent (6 min)
Stochastic Gradient Descent Convergence (12 min)
Online Learning (13 min)
Map Reduce and Data Parallelism (14 min)
Problem Description and Pipeline (7 min)
Week10終わった！やった！
----
以下は2周目の実績
Week10
Sliding Windows (15 min)
Getting Lots of Data and Artificial Data (16 min)
Ceiling Analysis: What Part of the Pipeline to Work on Next (14 min)
Summary and Thank You (5 min)
今回終わった物
Learning With Large Datasets (6 min)
Stochastic Gradient Descent (13 min)
Mini-Batch Gradient Descent (6 min)
Stochastic Gradient Descent Convergence (12 min)
Online Learning (13 min)
Map Reduce and Data Parallelism (14 min)
Problem Description and Pipeline (7 min)
----
Week9
Multivariate Gaussian Distribution (Optional) (14 min)
Anomaly Detection using the Multivariate Gaussian Distribution (Optional) (14 min)
今回終わった物
Content Based Recommendations (15 min)
Collaborative Filtering (10 min)
Collaborative Filtering Algorithm (9 min)
Vectorization: Low Rank Matrix Factorization (8 min)
Implementational Detail: Mean Normalization (9 min)
前回終わってる物
Problem Motivation (8 min)
Gaussian Distribution (10 min)
Algorithm (12 min)
Developing and Evaluating an Anomaly Detection System (13 min)
Anomaly Detection vs. Supervised Learning (8 min)
Choosing What Features to Use (12 min)
Problem Formulation (8 min)
-----
Week8
Choosing the Number of Principal Components (11 min)
Reconstruction from Compressed Representation (4 min)
Advice for Applying PCA (13 min)
後から終えた物
Choosing the Number of Clusters (8 min)
Motivation I: Data Compression (10 min)
Motivation II: Visualization (6 min)
Principal Component Analysis Problem Formulation (9 min)
Principal Component Analysis Algorithm (15 min)
今回終わった物
Optimization Objective (7 min)
Random Initialization (8 min)
前回終わってる物
Unsupervised Learning: Introduction (3 min)
K-Means Algorithm (13 min)
----
Week7
Mathematics Behind Large Margin Classification (Optional) (20 min)
Kernels I (16 min)
Kernels II (16 min)
Using An SVM (21 min)
前回終わってる物
Optimization Objective (15 min)
Large Margin Intuition (11 min)
この週はスキップ。
----
Week 6
Deciding What to Do Next Revisited (7 min)
Prioritizing What to Work On (10 min)
Error Analysis (13 min)
Error Metrics for Skewed Classes (12 min)
Trading Off Precision and Recall (14 min)
Data For Machine Learning (11 min)
今回終わった物
Learning Curves (12 min)
前回終わってる物
Completed Deciding What to Try Next (6 min)
Completed Evaluating a Hypothesis (8 min)
Completed Model Selection and Train/Validation/Test Sets (12 min)
Diagnosing Bias vs. Variance (8 min)
Regularization and Bias/Variance (11 min)
----
Week5
Gradient Checking (12 min)
Random Initialization (7 min)
Putting It Together (14 min)
Autonomous Driving (7 min)
done
Implementation Note: Unrolling Parameters (8 min)
前回終わってる物
Cost Function (7 min)
Backpropagation Algorithm (12 min)
Backpropagation Intuition (13 min)
今週は一本。もう一本くらいやりたかったけど、年末は仕方ないかなぁ。
-----
Week4
Examples and Intuitions I (7 min)
Examples and Intuitions II (10 min)
Multiclass Classification (4 min)
done
Model Representation II (12 min)
前回終わってる物
Non-linear Hypotheses (10 min)
Neurons and the Brain (8 min)
Model Representation I (12 min)
今週は私的な事情で進みが悪かったです。それでも一本終えたので残り三つ。
-----
Week 3
Multiclass Classification: One-vs-all (6 min)
The Problem of Overfitting (10 min)
Cost Function (10 min)
Regularized Linear Regression (11 min)
Regularized Logistic Regression (9 min)
done
Cost Function (11 min)
Simplified Cost Function and Gradient Descent (10 min)
Advanced Optimization (14 min)
前回終わってる物
Classification (8 min)
Hypothesis Representation (7 min)
Decision Boundary (15 min)
5本残ったけどもともとWeek3は前回たくさん残ってた週の一つなので、良く健闘したかなぁ。
一応前回訳した分と合わせると半分は超えた（6/11）
-----
Week 1, 2
-Features and Polynomial Regression (8 min)
-Normal Equation (16 min)
- Normal Equation Noninvertibility (Optional) (6 min)
今回終わった物
- Inverse and Transpose (11 min)
-Gradient Descent For Linear Regression (10 min)
-Descent in Practice II - Learning Rate (9 min)
3つ残りましたが、もうあと一歩ですね。
最初の週は線形代数の補講が大量にあるので大変でした。
----
以下は前回。
----
こっそりメモ。
終わった物
Algorithm (12 min)
Developing and Evaluating an Anomaly Detection System (13 min)
Choosing What Features to Use (12 min)
Problem Formulation (8 min)
----
2013年4月から、機械学習のコースを翻訳していきます。
ここには各週のステータスを書いていきます。
2013年6月4週
今週は2週間分一気にアップされたので膨大です。
Algorithm (12 min) *
Developing and Evaluating an Anomaly Detection System (13 min)
Anomaly Detection vs. Supervised Learning (8 min)
Choosing What Features to Use (12 min)
Multivariate Gaussian Distribution (Optional) (14 min)
Anomaly Detection using the Multivariate Gaussian Distribution (Optional) (14 min)
Problem Formulation (8 min)
Content Based Recommendations (15 min)
Collaborative Filtering (10 min)
Collaborative Filtering Algorithm (9 min)
Vectorization: Low Rank Matrix Factorization (8 min)
Implementational Detail: Mean Normalization (9 min)
Learning With Large Datasets (6 min)
Stochastic Gradient Descent (13 min)
Mini-Batch Gradient Descent (6 min)
Stochastic Gradient Descent Convergence (12 min)
Online Learning (13 min)
Map Reduce and Data Parallelism (14 min)
Problem Description and Pipeline (7 min)
Sliding Windows (15 min)
Getting Lots of Data and Artificial Data (16 min)
終わった物
Problem Motivation (8 min)
Gaussian Distribution (10 min)
----
2013年6月3週
今週は別件で時間を食われたので少しさぼり。
Optimization Objective (7 min)
Random Initialization (8 min)
Choosing the Number of Clusters (8 min)
Motivation I: Data Compression (10 min)
Motivation II: Visualization (6 min)
Principal Component Analysis Problem Formulation (9 min)
Principal Component Analysis Algorithm (15 min)
Choosing the Number of Principal Components (11 min)
Reconstruction from Compressed Representation (4 min)
Advice for Applying PCA (13 min)
終わった物
Unsupervised Learning: Introduction (3 min)
K-Means Algorithm (13 min)
----
2013年6月2週
今週は結構作業はしたのですが、英文の数が多くてあまり進みませんでした。
早口だったんでしょうかね？
Mathematics Behind Large Margin Classification (Optional) (20 min)
Kernels I (16 min)
Kernels II (16 min)
Using An SVM (21 min)
終わった物
Optimization Objective (15 min)
Large Margin Intuition (11 min)
----
2013年6月1週
今週は5動画も訳せたのですが、動画の数が多いので全体から見ると
5/12
でした。
Learning Curves (12 min)
Deciding What to Do Next Revisited (7 min)
Prioritizing What to Work On (10 min)
Error Analysis (13 min)
Error Metrics for Skewed Classes (12 min)
Trading Off Precision and Recall (14 min)
Data For Machine Learning (11 min)
終わった物
Completed Deciding What to Try Next (6 min)
Completed Evaluating a Hypothesis (8 min)
Completed Model Selection and Train/Validation/Test Sets (12 min)
Diagnosing Bias vs. Variance (8 min)
Regularization and Bias/Variance (11 min)
----
2013年5月4週
数としては3/8ですが、Unroll、Gradient Checking、Random Initialization、Autonomous Drivingは補講のような物なので、見た目よりは量こなせているかなぁ、と思います。
Completed Implementation Note: Unrolling Parameters (8 min)
Completed Gradient Checking (12 min)
Random Initialization (7 min)
Putting It Together (14 min)
Autonomous Driving (7 min)
終わった物
Completed Cost Function (7 min)
Completed Backpropagation Algorithm (12 min)
Completed Backpropagation Intuition (13 min)
----
2013年5月3週
3/7動画終わりました。
量的には半分に届いてませんが、Multiclass Classificationは短い動画なので実際は半分くらいは終わってます。
当面は半分を目標にやっていこうかな、と思いはじめています。
Model Representation II (12 min)
Examples and Intuitions I (7 min)
Examples and Intuitions II (10 min)
Multiclass Classification (4 min)
終わった物
Non-linear Hypotheses (10 min)
Neurons and the Brain (8 min)
Model Representation I (12 min)
----
2013年5月2週
3/11動画訳しました。
8動画も残ったけど、一週間に11動画はちょっと予想外でした。
二週間と勘違いしてた(^_^;)
後半は結構悪くないペースだったんですが、序盤に先週分の後始末が多かったのが敗因か。
今週はかなり手伝ってもらえました。感謝。
Cost Function (11 min)
Simplified Cost Function and Gradient Descent (10 min)
Advanced Optimization (14 min)
Multiclass Classification: One-vs-all (6 min)
The Problem of Overfitting (10 min)
Cost Function (10 min)
Regularized Linear Regression (11 min)
Regularized Logistic Regression (9 min)
終わった物
Classification (8 min)
Hypothesis Representation (7 min)
Decision Boundary (15 min)
----
2つほど作業中ですが、それらが終わるとすると6動画ほど残りました。
ちょっと私用が忙しかったので(^_^;)
----
今週はOptionalな物以外からやっていきます。
2013年4月4週
現在作業中の物には「＊」をつけておきます。
-Gradient Descent For Linear Regression (10 min)
-Descent in Practice II - Learning Rate (9 min)
-Features and Polynomial Regression (8 min)
-Normal Equation (16 min)
- Normal Equation Noninvertibility (Optional) (6 min)
Optionalな物
- Inverse and Transpose (11 min)
反映待ちな物
- Multiple Features (8 min)
- Matrix Vector Multiplication (14 min)
- Matrix Matrix Multiplication (11 min)
-Matrix Multiplication Properties (9 min)
- Gradient Descent in Practice I - Feature Scaling (9 min)
-What's Next (6 min)
- Gradient Descent for Multiple Variables (5 min)
