投稿

【李沐 & Alex 】伯克利深度学习Deep Learning UC Berkeley STAT-157 2019

9916

4

2019-01-26 00:24:45

https://www.youtube.com/playlist?list=PLZSO_6-bSqHQHBCoGaObUljoXAyyqhpFW

听君一席课发消息

助力B站双一流。

闲来无事玩这款传奇，打怪升级，解压又有趣，时间过得快！

PC点我玩玩>>

L1_1 Logistics

16:45

L1_2 Deep Learning Overview

06:54

L1_3 Software

09:31

L1_4 Linear Algebra

19:22

L1_5 Linear Algebra in Jupyter

13:47

L2_1 NDArrays

27:30

L2_2 AWS EC2 Instances

12:25

L2_3 Basic Probability

15:25

L2_4 Basic Probability Jupyter

03:28

L2_5 Naive Bayes

13:23

L2_6 Naive Bayes Jupyter

05:14

L3_1 Sampling

18:06

L3_2 Sampling in Jupyter

08:59

L3_3 Setting up a GPU instance on AWS

23:12

L3_4 Automatic Differentiation

16:26

L4_1 Linear Regression

15:56

L5_1 Homework and Project Logistics

11:13

L5_2 Maximum Likelihood and Maximum a Posteriori

18:35

L5_3 Loss Functions

08:08

L5_4 Logistic Regression

17:19

L5_5 Logistic Regression in Jupyter

06:09

L5_6 Information Theory

17:37

L5_7 Information Theory Recap

15:50

L5_8 Softmax Classification in Python

18:57

L5_8b Softmax Classification in Python (Gluon version)

04:01

L6_1 Perceptron Algorithm

17:56

L6_2 Multilayer Perceptron

11:17

L6_3 Multilayer Perceptron in Python

09:43

L7_1 Model Evaluation, Overfitting and Underfitting

28:57

L7_2 Squared L2 Regularization

04:03

L7_3 Squared L2 Regularization in Jupyter

04:50

L7_4 Dropout

04:53

L7_5 Dropout in Jupyter

09:47

L8_1 Gradient Exploding and Vanishing

10:01

L8_3 Stabilize Training - Activations

05:24

L8_4 Numerical Stability Notebook

09:23

L8_5 Deep Learning Hardware

19:40

L8_6 Advanced Deep Learning Hardware

13:29

L9_1 Empirical and Expected Risk

11:13

L9_2 Covariate Shift

09:18

L9_3 Covariate Shift and Bias

06:22

L9_4 Logistic Regression

07:29

L9_5 Covariate Shift Correction

09:34

L9_6 Label Shift

05:06

L9_7 Adversarial Data

07:47

L9_8 Nonstationary Environment

08:18

L10_1 Deep Learning Frameworks, Gluon (1)

12:35

L10_1 Deep Learning Frameworks, Gluon

12:35

L10_2 Blocks and Layers

11:31

L10_3 Managing Parameters

09:18

L10_5 Using GPUs

05:47

L10_6 Customized Layers

06:36

L10_7 Deferred Initialization

05:15

L11_2 Convolutions

29:02

L11_4 Padding and Stride

08:15

L11_5 Padding and Stride in Python

05:01

L11_6 Channels

07:51

L11_7 Channels in Python

05:19

L11_8 Pooling

04:49

L11_9 Pooling in Python

05:37

L12_1 LeNet

07:05

L12_2 LeNet in Python

09:45

L12_3 AlexNet

13:17

L12_4 AlexNet in Python

08:11

L12_6 VGG in Python

05:28

L12_7 Network in Network (NiN)

06:54

L12_8 Network in Network (NiN) in Python

04:06

L13_1 Inception (GoogLeNet)

29:44

L13_2 Inception in Python

10:47

L13_3 Batch Normalization

08:25

L13_4 Batch Normalization in Python

10:46

L13_5 ResNet (Residual Networks)

13:46

L13_6 ResNet in Python

16:02

L13_7 Beyound ResNet

21:18

L13_8 DenseNet in Python

10:46

L14_1 Midterm Logistics

08:40

L14_2 Hybridization (Just in Time Compilation)

06:08

L14_3 Hybridization in Python

13:46

L14_6 Multi-GPU Training in Python

14:44

L14_7 Multi-Machine Training

19:30

L15_1 Image Augmentation

06:13

L15_2 Fine Tuning

11:34

L15_3 Fine Tuning in Python

10:12

L15_4 Style Transfer

07:25

L15_5 Style Transfer in Python

08:41

L16_1 Object Detection

18:53

L16_2 Bounding and Anchor Boxes

11:46

L16_3 Object Detection Dataset

03:39

L16_4 Region-based CNNs

14:35

L16_5 SSD and YOLO

08:35

L16_6 Bag of Tricks for CNN Training

20:16

L16_7 SSD in Python

31:08

L18_1 Dependent Random Variables

12:02

L18_2 Sequence Models

15:26

L18_3 Markov Assumption & Autoregressive Models

13:36

L18_4 Language Modeling Basics

13:48

L18_5 Text Preprocessing

16:19

L19_1 Recurrent Neural Networks

08:44

L19_2 Recurrent Neural Networks in Python

37:53

L19_3 RNN Mechanics

08:26

L19_4 Recurrent Neural Networks in Gluon

16:05

L19_5 Truncated Backprop through Time

26:54

L19_6 Gated Recurrent Unit (GRU)

17:49

L19_7 Gated Recurrent Unit in Python

15:30

L19_8 Long Short Term Memory

07:15

L19_9 Long Short Term Memory in Python

05:15

顶部