|
Обратите внимание, что наш сайт не размещает какие-либо файлы из списка. Вы не можете скачать
эти файлы или скачать torrent-файл.
|
| [CourseClub.ME].url |
122б |
| [FCS Forum].url |
133б |
| [FreeCourseSite.com].url |
127б |
| [GigaCourse.Com].url |
49б |
| 001 Anatomy of a torch dataset and dataloader.en.srt |
26.46Кб |
| 001 Anatomy of a torch dataset and dataloader.mp4 |
135.84Мб |
| 001 Bonus content.html |
4.45Кб |
| 001 Convolution_ concepts.en.srt |
32.50Кб |
| 001 Convolution_ concepts.mp4 |
98.06Мб |
| 001 Downloading and using the code.en.srt |
9.41Кб |
| 001 Downloading and using the code.mp4 |
45.65Мб |
| 001 Explanation of weight matrix sizes.en.srt |
17.18Кб |
| 001 Explanation of weight matrix sizes.mp4 |
68.98Мб |
| 001 GAN_ What, why, and how.en.srt |
23.51Кб |
| 001 GAN_ What, why, and how.mp4 |
89.74Мб |
| 001 How to learn from the Python tutorial.en.srt |
4.83Кб |
| 001 How to learn from the Python tutorial.mp4 |
21.97Мб |
| 001 How to learn from this course.mp4 |
54.97Мб |
| 001 How to learn topic _X_ in deep learning_.en.srt |
12.32Кб |
| 001 How to learn topic _X_ in deep learning_.mp4 |
42.03Мб |
| 001 If-else statements.en.srt |
21.71Кб |
| 001 If-else statements.mp4 |
66.80Мб |
| 001 Indexing.en.srt |
18.10Кб |
| 001 Indexing.mp4 |
51.07Мб |
| 001 Inputs and outputs.en.srt |
10.56Кб |
| 001 Inputs and outputs.mp4 |
29.49Мб |
| 001 Introduction to this section.en.srt |
2.90Кб |
| 001 Introduction to this section.mp4 |
11.12Мб |
| 001 Overview of gradient descent.en.srt |
20.89Кб |
| 001 Overview of gradient descent.mp4 |
68.44Мб |
| 001 Printing and string interpolation.en.srt |
24.33Кб |
| 001 Printing and string interpolation.mp4 |
94.83Мб |
| 001 Project 1_ A gratuitously complex adding machine.en.srt |
10.75Кб |
| 001 Project 1_ A gratuitously complex adding machine.mp4 |
48.55Мб |
| 001 Project 1_ Import and classify CIFAR10.en.srt |
10.56Кб |
| 001 Project 1_ Import and classify CIFAR10.mp4 |
48.36Мб |
| 001 Regularization_ Concept and methods.en.srt |
19.02Кб |
| 001 Regularization_ Concept and methods.mp4 |
80.05Мб |
| 001 Should you watch the Python tutorial_.en.srt |
6.14Кб |
| 001 Should you watch the Python tutorial_.mp4 |
23.77Мб |
| 001 The canonical CNN architecture.en.srt |
15.68Кб |
| 001 The canonical CNN architecture.mp4 |
55.83Мб |
| 001 The perceptron and ANN architecture.en.srt |
26.80Кб |
| 001 The perceptron and ANN architecture.mp4 |
83.64Мб |
| 001 Transfer learning_ What, why, and when_.en.srt |
24.76Кб |
| 001 Transfer learning_ What, why, and when_.mp4 |
96.61Мб |
| 001 Two perspectives of the world.en.srt |
10.32Кб |
| 001 Two perspectives of the world.mp4 |
40.01Мб |
| 001 What are _metaparameters__.en.srt |
7.35Кб |
| 001 What are _metaparameters__.mp4 |
32.70Мб |
| 001 What are autoencoders and what do they do_.en.srt |
16.93Кб |
| 001 What are autoencoders and what do they do_.mp4 |
49.04Мб |
| 001 What are fully-connected and feedforward networks_.en.srt |
6.94Кб |
| 001 What are fully-connected and feedforward networks_.mp4 |
25.53Мб |
| 001 What is a GPU and why use it_.en.srt |
22.47Кб |
| 001 What is a GPU and why use it_.mp4 |
88.73Мб |
| 001 What is an artificial neural network_.en.srt |
21.30Кб |
| 001 What is an artificial neural network_.mp4 |
65.38Мб |
| 001 What is overfitting and is it as bad as they say_.en.srt |
18.32Кб |
| 001 What is overfitting and is it as bad as they say_.mp4 |
73.13Мб |
| 001 What is style transfer and how does it work_.en.srt |
6.35Кб |
| 001 What is style transfer and how does it work_.mp4 |
40.57Мб |
| 001 Will AI save us or destroy us_.en.srt |
14.36Кб |
| 001 Will AI save us or destroy us_.mp4 |
65.92Мб |
| 002 Accuracy, precision, recall, F1.en.srt |
18.08Кб |
| 002 Accuracy, precision, recall, F1.mp4 |
72.57Мб |
| 002 A geometric view of ANNs.en.srt |
19.37Кб |
| 002 A geometric view of ANNs.mp4 |
70.88Мб |
| 002 A surprising demo of weight initializations.en.srt |
23.89Кб |
| 002 A surprising demo of weight initializations.mp4 |
121.57Мб |
| 002 CNN to classify MNIST digits.en.srt |
38.02Кб |
| 002 CNN to classify MNIST digits.mp4 |
200.33Мб |
| 002 Cross-validation.en.srt |
24.96Кб |
| 002 Cross-validation.mp4 |
88.19Мб |
| 002 Data size and network size.en.srt |
23.39Кб |
| 002 Data size and network size.mp4 |
135.67Мб |
| 002 Denoising MNIST.en.srt |
22.79Кб |
| 002 Denoising MNIST.mp4 |
118.53Мб |
| 002 Example case studies.en.srt |
9.15Кб |
| 002 Example case studies.mp4 |
52.92Мб |
| 002 Feature maps and convolution kernels.en.srt |
13.96Кб |
| 002 Feature maps and convolution kernels.mp4 |
70.41Мб |
| 002 How models _learn_.en.srt |
18.75Кб |
| 002 How models _learn_.mp4 |
72.79Мб |
| 002 How to read academic DL papers.en.srt |
25.43Кб |
| 002 How to read academic DL papers.mp4 |
141.85Мб |
| 002 If-else statements, part 2.en.srt |
22.90Кб |
| 002 If-else statements, part 2.mp4 |
91.12Мб |
| 002 Implementation.en.srt |
14.81Кб |
| 002 Implementation.mp4 |
76.60Мб |
| 002 Linear GAN with MNIST.en.srt |
31.99Кб |
| 002 Linear GAN with MNIST.mp4 |
169.90Мб |
| 002 My policy on code-sharing.en.srt |
2.52Кб |
| 002 My policy on code-sharing.mp4 |
10.24Мб |
| 002 Plotting dots and lines.en.srt |
17.70Кб |
| 002 Plotting dots and lines.mp4 |
53.87Мб |
| 002 Project 1_ My solution.en.srt |
16.97Кб |
| 002 Project 1_ My solution.en.srt |
17.15Кб |
| 002 Project 1_ My solution.mp4 |
99.75Мб |
| 002 Project 1_ My solution.mp4 |
118.60Мб |
| 002 Python libraries (numpy).en.srt |
20.01Кб |
| 002 Python libraries (numpy).mp4 |
63.39Мб |
| 002 Slicing.en.srt |
17.97Кб |
| 002 Slicing.mp4 |
48.45Мб |
| 002 Spectral theories in mathematics.en.srt |
13.58Кб |
| 002 Spectral theories in mathematics.mp4 |
51.06Мб |
| 002 The _wine quality_ dataset.en.srt |
25.71Кб |
| 002 The _wine quality_ dataset.mp4 |
143.50Мб |
| 002 The Gram matrix (feature activation covariance).en.srt |
16.79Кб |
| 002 The Gram matrix (feature activation covariance).mp4 |
66.49Мб |
| 002 The MNIST dataset.en.srt |
18.71Кб |
| 002 The MNIST dataset.mp4 |
101.46Мб |
| 002 train() and eval() modes.en.srt |
10.19Кб |
| 002 train() and eval() modes.mp4 |
38.34Мб |
| 002 Transfer learning_ MNIST -_ FMNIST.en.srt |
14.58Кб |
| 002 Transfer learning_ MNIST -_ FMNIST.mp4 |
90.35Мб |
| 002 Using Udemy like a pro.en.srt |
12.34Кб |
| 002 Using Udemy like a pro.mp4 |
54.37Мб |
| 002 Variables.en.srt |
27.29Кб |
| 002 Variables.mp4 |
77.58Мб |
| 002 What about local minima_.en.srt |
17.17Кб |
| 002 What about local minima_.mp4 |
67.08Мб |
| 003 ANN math part 1 (forward prop).en.srt |
17.39Кб |
| 003 ANN math part 1 (forward prop).mp4 |
57.90Мб |
| 003 APRF in code.en.srt |
9.38Кб |
| 003 APRF in code.mp4 |
51.79Мб |
| 003 CNN on shifted MNIST.en.srt |
12.12Кб |
| 003 CNN on shifted MNIST.mp4 |
58.34Мб |
| 003 CodeChallenge_ How many units_.en.srt |
28.86Кб |
| 003 CodeChallenge_ How many units_.mp4 |
135.38Мб |
| 003 CodeChallenge_ letters to numbers.en.srt |
20.54Кб |
| 003 CodeChallenge_ letters to numbers.mp4 |
118.74Мб |
| 003 CodeChallenge_ Linear GAN with FMNIST.en.srt |
13.88Кб |
| 003 CodeChallenge_ Linear GAN with FMNIST.mp4 |
62.73Мб |
| 003 CodeChallenge_ Minibatch size in the wine dataset.en.srt |
23.05Кб |
| 003 CodeChallenge_ Minibatch size in the wine dataset.mp4 |
118.79Мб |
| 003 CodeChallenge_ Run an experiment on the GPU.en.srt |
9.81Кб |
| 003 CodeChallenge_ Run an experiment on the GPU.mp4 |
52.99Мб |
| 003 CodeChallenge_ unbalanced data.en.srt |
29.32Кб |
| 003 CodeChallenge_ unbalanced data.mp4 |
166.26Мб |
| 003 Convolution in code.en.srt |
30.53Кб |
| 003 Convolution in code.mp4 |
173.10Мб |
| 003 Dropout regularization.en.srt |
31.17Кб |
| 003 Dropout regularization.mp4 |
136.03Мб |
| 003 DUDL_PythonCode.zip |
700.80Кб |
| 003 FFN to classify digits.en.srt |
32.91Кб |
| 003 FFN to classify digits.mp4 |
161.85Мб |
| 003 For loops.en.srt |
25.24Кб |
| 003 For loops.mp4 |
87.13Мб |
| 003 Generalization.en.srt |
8.82Кб |
| 003 Generalization.mp4 |
32.44Мб |
| 003 Gradient descent in 1D.en.srt |
24.75Кб |
| 003 Gradient descent in 1D.mp4 |
119.29Мб |
| 003 Math and printing.en.srt |
26.80Кб |
| 003 Math and printing.mp4 |
78.50Мб |
| 003 Project 2_ CIFAR-autoencoder.en.srt |
7.00Кб |
| 003 Project 2_ CIFAR-autoencoder.mp4 |
33.37Мб |
| 003 Project 2_ Predicting heart disease.en.srt |
10.99Кб |
| 003 Project 2_ Predicting heart disease.mp4 |
50.61Мб |
| 003 Python libraries (pandas).en.srt |
20.30Кб |
| 003 Python libraries (pandas).mp4 |
81.19Мб |
| 003 Some other possible ethical scenarios.en.srt |
15.20Кб |
| 003 Some other possible ethical scenarios.mp4 |
66.25Мб |
| 003 Subplot geometry.en.srt |
23.14Кб |
| 003 Subplot geometry.mp4 |
86.78Мб |
| 003 Terms and datatypes in math and computers.en.srt |
10.68Кб |
| 003 Terms and datatypes in math and computers.mp4 |
38.08Мб |
| 003 Theory_ Why and how to initialize weights.en.srt |
18.23Кб |
| 003 Theory_ Why and how to initialize weights.mp4 |
79.41Мб |
| 003 The role of DL in science and knowledge.en.srt |
23.31Кб |
| 003 The role of DL in science and knowledge.mp4 |
121.55Мб |
| 003 The style transfer algorithm.en.srt |
15.10Кб |
| 003 The style transfer algorithm.mp4 |
67.31Мб |
| 004 AEs for occlusion.en.srt |
25.42Кб |
| 004 AEs for occlusion.mp4 |
138.20Мб |
| 004 ANN math part 2 (errors, loss, cost).en.srt |
13.89Кб |
| 004 ANN math part 2 (errors, loss, cost).mp4 |
48.47Мб |
| 004 APRF example 1_ wine quality.en.srt |
19.25Кб |
| 004 APRF example 1_ wine quality.mp4 |
107.35Мб |
| 004 Classify Gaussian blurs.en.srt |
34.26Кб |
| 004 Classify Gaussian blurs.mp4 |
185.14Мб |
| 004 CNN GAN with Gaussians.en.srt |
22.13Кб |
| 004 CNN GAN with Gaussians.mp4 |
135.70Мб |
| 004 CodeChallenge_ Binarized MNIST images.en.srt |
7.37Кб |
| 004 CodeChallenge_ Binarized MNIST images.mp4 |
40.78Мб |
| 004 CodeChallenge_ unfortunate starting value.en.srt |
16.00Кб |
| 004 CodeChallenge_ unfortunate starting value.mp4 |
77.09Мб |
| 004 CodeChallenge_ Weight variance inits.en.srt |
18.42Кб |
| 004 CodeChallenge_ Weight variance inits.mp4 |
103.96Мб |
| 004 Converting reality to numbers.en.srt |
9.57Кб |
| 004 Converting reality to numbers.mp4 |
33.21Мб |
| 004 Convolution parameters (stride, padding).en.srt |
18.09Кб |
| 004 Convolution parameters (stride, padding).mp4 |
66.93Мб |
| 004 Cross-validation -- manual separation.en.srt |
18.59Кб |
| 004 Cross-validation -- manual separation.mp4 |
98.30Мб |
| 004 Data normalization.en.srt |
19.68Кб |
| 004 Data normalization.mp4 |
59.81Мб |
| 004 Dropout regularization in practice.en.srt |
33.37Кб |
| 004 Dropout regularization in practice.mp4 |
183.23Мб |
| 004 Enumerate and zip.en.srt |
16.03Кб |
| 004 Enumerate and zip.mp4 |
58.59Мб |
| 004 Famous CNN architectures.en.srt |
8.70Кб |
| 004 Famous CNN architectures.mp4 |
41.28Мб |
| 004 Getting help on functions.en.srt |
11.05Кб |
| 004 Getting help on functions.mp4 |
48.60Мб |
| 004 Lists (1 of 2).en.srt |
20.48Кб |
| 004 Lists (1 of 2).mp4 |
55.04Мб |
| 004 Making the graphs look nicer.en.srt |
26.98Кб |
| 004 Making the graphs look nicer.mp4 |
107.66Мб |
| 004 Project 2_ My solution.en.srt |
27.78Кб |
| 004 Project 2_ My solution.mp4 |
155.73Мб |
| 004 Project 3_ FMNIST.en.srt |
5.11Кб |
| 004 Project 3_ FMNIST.mp4 |
26.45Мб |
| 004 Running experiments to understand DL.en.srt |
19.22Кб |
| 004 Running experiments to understand DL.mp4 |
74.84Мб |
| 004 Transferring the screaming bathtub.en.srt |
32.28Кб |
| 004 Transferring the screaming bathtub.mp4 |
216.82Мб |
| 004 What to do about unbalanced designs_.mp4 |
54.21Мб |
| 004 Will deep learning take our jobs_.en.srt |
14.90Кб |
| 004 Will deep learning take our jobs_.mp4 |
75.14Мб |
| 005 Accountability and making ethical AI.en.srt |
16.71Кб |
| 005 Accountability and making ethical AI.mp4 |
70.06Мб |
| 005 ANN math part 3 (backprop).en.srt |
15.23Кб |
| 005 ANN math part 3 (backprop).mp4 |
52.89Мб |
| 005 APRF example 2_ MNIST.en.srt |
17.17Кб |
| 005 APRF example 2_ MNIST.mp4 |
98.62Мб |
| 005 Are artificial _neurons_ like biological neurons_.en.srt |
24.16Кб |
| 005 Are artificial _neurons_ like biological neurons_.mp4 |
114.65Мб |
| 005 CodeChallenge_ Data normalization.en.srt |
24.48Кб |
| 005 CodeChallenge_ Data normalization.mp4 |
96.25Мб |
| 005 CodeChallenge_ Gaussians with fewer layers.en.srt |
8.94Кб |
| 005 CodeChallenge_ Gaussians with fewer layers.mp4 |
53.06Мб |
| 005 CodeChallenge_ Style transfer with AlexNet.en.srt |
10.47Кб |
| 005 CodeChallenge_ Style transfer with AlexNet.mp4 |
53.47Мб |
| 005 Continue.en.srt |
10.09Кб |
| 005 Continue.mp4 |
33.03Мб |
| 005 Creating functions.en.srt |
30.89Кб |
| 005 Creating functions.mp4 |
88.43Мб |
| 005 Cross-validation -- scikitlearn.en.srt |
30.46Кб |
| 005 Cross-validation -- scikitlearn.mp4 |
142.88Мб |
| 005 Data oversampling in MNIST.en.srt |
24.16Кб |
| 005 Data oversampling in MNIST.mp4 |
122.59Мб |
| 005 Dropout example 2.en.srt |
9.18Кб |
| 005 Dropout example 2.mp4 |
53.87Мб |
| 005 Examine feature map activations.en.srt |
40.51Кб |
| 005 Examine feature map activations.mp4 |
260.56Мб |
| 005 Gradient descent in 2D.en.srt |
21.35Кб |
| 005 Gradient descent in 2D.mp4 |
95.90Мб |
| 005 Lists (2 of 2).en.srt |
14.58Кб |
| 005 Lists (2 of 2).mp4 |
46.69Мб |
| 005 Project 3_ FFN for missing data interpolation.en.srt |
14.38Кб |
| 005 Project 3_ FFN for missing data interpolation.mp4 |
45.39Мб |
| 005 Project 4_ Psychometric functions in CNNs.en.srt |
16.88Кб |
| 005 Project 4_ Psychometric functions in CNNs.mp4 |
76.27Мб |
| 005 Seaborn.en.srt |
15.73Кб |
| 005 Seaborn.mp4 |
59.72Мб |
| 005 The Conv2 class in PyTorch.en.srt |
18.90Кб |
| 005 The Conv2 class in PyTorch.mp4 |
100.19Мб |
| 005 The importance of data normalization.en.srt |
13.75Кб |
| 005 The importance of data normalization.mp4 |
64.65Мб |
| 005 The latent code of MNIST.en.srt |
31.66Кб |
| 005 The latent code of MNIST.mp4 |
161.81Мб |
| 005 Transfer learning with ResNet-18.en.srt |
24.59Кб |
| 005 Transfer learning with ResNet-18.mp4 |
148.46Мб |
| 005 Vector and matrix transpose.en.srt |
10.01Кб |
| 005 Vector and matrix transpose.mp4 |
37.66Мб |
| 005 Xavier and Kaiming initializations.en.srt |
22.52Кб |
| 005 Xavier and Kaiming initializations.mp4 |
134.08Мб |
| 006 ANN for regression.en.srt |
35.85Кб |
| 006 ANN for regression.mp4 |
135.50Мб |
| 006 Autoencoder with tied weights.en.srt |
34.83Кб |
| 006 Autoencoder with tied weights.mp4 |
177.74Мб |
| 006 Batch normalization.en.srt |
18.66Кб |
| 006 Batch normalization.mp4 |
76.81Мб |
| 006 CNN GAN with FMNIST.en.srt |
9.23Кб |
| 006 CNN GAN with FMNIST.mp4 |
54.58Мб |
| 006 CodeChallenge_ 2D gradient ascent.en.srt |
7.53Кб |
| 006 CodeChallenge_ 2D gradient ascent.mp4 |
39.36Мб |
| 006 CodeChallenge_ Choose the parameters.en.srt |
10.12Кб |
| 006 CodeChallenge_ Choose the parameters.mp4 |
58.71Мб |
| 006 CodeChallenge_ MNIST with unequal groups.en.srt |
12.70Кб |
| 006 CodeChallenge_ MNIST with unequal groups.mp4 |
62.37Мб |
| 006 CodeChallenge_ Softcode internal parameters.en.srt |
25.03Кб |
| 006 CodeChallenge_ Softcode internal parameters.mp4 |
120.10Мб |
| 006 CodeChallenge_ VGG-16.en.srt |
5.05Кб |
| 006 CodeChallenge_ VGG-16.mp4 |
20.28Мб |
| 006 CodeChallenge_ Xavier vs. Kaiming.en.srt |
24.65Кб |
| 006 CodeChallenge_ Xavier vs. Kaiming.mp4 |
126.50Мб |
| 006 Cross-validation -- DataLoader.en.srt |
28.57Кб |
| 006 Cross-validation -- DataLoader.mp4 |
172.32Мб |
| 006 Data noise augmentation (with devset+test).en.srt |
18.62Кб |
| 006 Data noise augmentation (with devset+test).mp4 |
106.09Мб |
| 006 Distributions of weights pre- and post-learning.en.srt |
22.05Кб |
| 006 Distributions of weights pre- and post-learning.mp4 |
116.26Мб |
| 006 Global and local variable scopes.en.srt |
19.67Кб |
| 006 Global and local variable scopes.mp4 |
65.96Мб |
| 006 Images.en.srt |
25.75Кб |
| 006 Images.mp4 |
93.56Мб |
| 006 Initializing variables.en.srt |
25.61Кб |
| 006 Initializing variables.mp4 |
91.05Мб |
| 006 OMG it's the dot product!.en.srt |
13.95Кб |
| 006 OMG it's the dot product!.mp4 |
50.11Мб |
| 006 Project 3_ My solution.en.srt |
11.88Кб |
| 006 Project 3_ My solution.mp4 |
75.48Мб |
| 006 Tuples.en.srt |
12.04Кб |
| 006 Tuples.mp4 |
35.75Мб |
| 006 Weight regularization (L1_L2)_ math.en.srt |
27.07Кб |
| 006 Weight regularization (L1_L2)_ math.mp4 |
85.41Мб |
| 007 Batch normalization in practice.en.srt |
11.05Кб |
| 007 Batch normalization in practice.mp4 |
61.76Мб |
| 007 Booleans.en.srt |
27.78Кб |
| 007 Booleans.mp4 |
76.83Мб |
| 007 CodeChallenge_ CNN GAN with CIFAR.en.srt |
11.65Кб |
| 007 CodeChallenge_ CNN GAN with CIFAR.mp4 |
60.77Мб |
| 007 CodeChallenge_ How wide the FC_.en.srt |
16.49Кб |
| 007 CodeChallenge_ How wide the FC_.mp4 |
94.08Мб |
| 007 CodeChallenge_ Identically random weights.en.srt |
17.92Кб |
| 007 CodeChallenge_ Identically random weights.mp4 |
88.17Мб |
| 007 CodeChallenge_ manipulate regression slopes.en.srt |
28.31Кб |
| 007 CodeChallenge_ manipulate regression slopes.mp4 |
139.12Мб |
| 007 CodeChallenge_ MNIST and breadth vs. depth.en.srt |
17.73Кб |
| 007 CodeChallenge_ MNIST and breadth vs. depth.mp4 |
95.21Мб |
| 007 Computation time.en.srt |
14.26Кб |
| 007 Computation time.mp4 |
81.73Мб |
| 007 Copies and referents of variables.en.srt |
7.24Кб |
| 007 Copies and referents of variables.mp4 |
23.78Мб |
| 007 Data feature augmentation.en.srt |
28.32Кб |
| 007 Data feature augmentation.mp4 |
158.27Мб |
| 007 Export plots in low and high resolution.en.srt |
11.37Кб |
| 007 Export plots in low and high resolution.mp4 |
43.57Мб |
| 007 L2 regularization in practice.en.srt |
18.97Кб |
| 007 L2 regularization in practice.mp4 |
110.47Мб |
| 007 Matrix multiplication.en.srt |
20.60Кб |
| 007 Matrix multiplication.mp4 |
85.67Мб |
| 007 Parametric experiments on g.d.en.srt |
27.15Кб |
| 007 Parametric experiments on g.d.mp4 |
135.61Мб |
| 007 Pretraining with autoencoders.en.srt |
28.75Кб |
| 007 Pretraining with autoencoders.mp4 |
156.58Мб |
| 007 Single-line loops (list comprehension).en.srt |
21.74Кб |
| 007 Single-line loops (list comprehension).mp4 |
75.14Мб |
| 007 Splitting data into train, devset, test.en.srt |
13.82Кб |
| 007 Splitting data into train, devset, test.mp4 |
79.21Мб |
| 007 Transpose convolution.en.srt |
19.91Кб |
| 007 Transpose convolution.mp4 |
92.89Мб |
| 008 ANN for classifying qwerties.en.srt |
34.00Кб |
| 008 ANN for classifying qwerties.mp4 |
151.12Мб |
| 008 Better performance in test than train_.en.srt |
11.95Кб |
| 008 Better performance in test than train_.mp4 |
44.83Мб |
| 008 CIFAR10 with autoencoder-pretrained model.en.srt |
25.89Кб |
| 008 CIFAR10 with autoencoder-pretrained model.mp4 |
153.34Мб |
| 008 Classes and object-oriented programming.en.srt |
26.60Кб |
| 008 Classes and object-oriented programming.mp4 |
108.18Мб |
| 008 CodeChallenge_ Batch-normalize the qwerties.en.srt |
7.52Кб |
| 008 CodeChallenge_ Batch-normalize the qwerties.mp4 |
41.43Мб |
| 008 CodeChallenge_ fixed vs. dynamic learning rate.en.srt |
23.05Кб |
| 008 CodeChallenge_ fixed vs. dynamic learning rate.mp4 |
114.56Мб |
| 008 CodeChallenge_ Optimizers and MNIST.en.srt |
9.92Кб |
| 008 CodeChallenge_ Optimizers and MNIST.mp4 |
46.26Мб |
| 008 Cross-validation on regression.en.srt |
11.99Кб |
| 008 Cross-validation on regression.mp4 |
60.35Мб |
| 008 Dictionaries.en.srt |
17.06Кб |
| 008 Dictionaries.mp4 |
50.67Мб |
| 008 Do autoencoders clean Gaussians_.en.srt |
24.39Кб |
| 008 Do autoencoders clean Gaussians_.mp4 |
147.88Мб |
| 008 Freezing weights during learning.en.srt |
19.25Кб |
| 008 Freezing weights during learning.mp4 |
93.15Мб |
| 008 Getting data into colab.en.srt |
8.85Кб |
| 008 Getting data into colab.mp4 |
43.75Мб |
| 008 L1 regularization in practice.en.srt |
17.44Кб |
| 008 L1 regularization in practice.mp4 |
99.44Мб |
| 008 Max_mean pooling.en.srt |
26.69Кб |
| 008 Max_mean pooling.mp4 |
89.07Мб |
| 008 Softmax.en.srt |
27.76Кб |
| 008 Softmax.mp4 |
95.96Мб |
| 008 while loops.en.srt |
27.94Кб |
| 008 while loops.mp4 |
91.10Мб |
| 009 Activation functions.en.srt |
26.49Кб |
| 009 Activation functions.mp4 |
97.03Мб |
| 009 Broadcasting in numpy.en.srt |
21.34Кб |
| 009 Broadcasting in numpy.mp4 |
71.05Мб |
| 009 CodeChallenge_ AEs and occluded Gaussians.en.srt |
14.03Кб |
| 009 CodeChallenge_ AEs and occluded Gaussians.mp4 |
89.45Мб |
| 009 Learning rates comparison.en.srt |
36.24Кб |
| 009 Learning rates comparison.mp4 |
168.64Мб |
| 009 Learning-related changes in weights.en.srt |
32.77Кб |
| 009 Learning-related changes in weights.mp4 |
146.78Мб |
| 009 Logarithms.en.srt |
11.47Кб |
| 009 Logarithms.mp4 |
43.88Мб |
| 009 Pooling in PyTorch.en.srt |
19.63Кб |
| 009 Pooling in PyTorch.mp4 |
81.02Мб |
| 009 Save and load trained models.en.srt |
8.95Кб |
| 009 Save and load trained models.mp4 |
55.71Мб |
| 009 Scrambled MNIST.en.srt |
11.24Кб |
| 009 Scrambled MNIST.mp4 |
60.17Мб |
| 009 Training in mini-batches.en.srt |
16.88Кб |
| 009 Training in mini-batches.mp4 |
62.12Мб |
| 009 Vanishing and exploding gradients.en.srt |
9.06Кб |
| 009 Vanishing and exploding gradients.mp4 |
30.24Мб |
| 010 Activation functions in PyTorch.en.srt |
16.95Кб |
| 010 Activation functions in PyTorch.mp4 |
91.46Мб |
| 010 Batch training in action.en.srt |
15.65Кб |
| 010 Batch training in action.mp4 |
89.10Мб |
| 010 CodeChallenge_ Custom loss functions.en.srt |
29.89Кб |
| 010 CodeChallenge_ Custom loss functions.mp4 |
132.89Мб |
| 010 Entropy and cross-entropy.mp4 |
106.00Мб |
| 010 Function error checking and handling.en.srt |
25.36Кб |
| 010 Function error checking and handling.mp4 |
99.87Мб |
| 010 Multilayer ANN.en.srt |
29.40Кб |
| 010 Multilayer ANN.mp4 |
144.70Мб |
| 010 Save the best-performing model.en.srt |
21.98Кб |
| 010 Save the best-performing model.mp4 |
126.50Мб |
| 010 Shifted MNIST.en.srt |
16.47Кб |
| 010 Shifted MNIST.mp4 |
77.91Мб |
| 010 Tangent_ Notebook revision history.en.srt |
2.76Кб |
| 010 Tangent_ Notebook revision history.mp4 |
22.18Мб |
| 010 To pool or to stride_.en.srt |
14.28Кб |
| 010 To pool or to stride_.mp4 |
55.51Мб |
| 010 Use default inits or apply your own_.en.srt |
6.34Кб |
| 010 Use default inits or apply your own_.mp4 |
28.05Мб |
| 011 Activation functions comparison.en.srt |
13.59Кб |
| 011 Activation functions comparison.mp4 |
73.90Мб |
| 011 CodeChallenge_ The mystery of the missing 7.en.srt |
15.78Кб |
| 011 CodeChallenge_ The mystery of the missing 7.mp4 |
74.25Мб |
| 011 Discover the Gaussian parameters.en.srt |
23.25Кб |
| 011 Discover the Gaussian parameters.mp4 |
136.65Мб |
| 011 Image transforms.en.srt |
23.92Кб |
| 011 Image transforms.mp4 |
129.90Мб |
| 011 Linear solutions to linear problems.en.srt |
12.17Кб |
| 011 Linear solutions to linear problems.mp4 |
50.37Мб |
| 011 Min_max and argmin_argmax.en.srt |
18.16Кб |
| 011 Min_max and argmin_argmax.mp4 |
88.21Мб |
| 011 The importance of equal batch sizes.en.srt |
9.47Кб |
| 011 The importance of equal batch sizes.mp4 |
60.11Мб |
| 011 Where to find online datasets.en.srt |
8.19Кб |
| 011 Where to find online datasets.mp4 |
41.70Мб |
| 012 CodeChallenge_ Compare relu variants.en.srt |
11.29Кб |
| 012 CodeChallenge_ Compare relu variants.mp4 |
63.97Мб |
| 012 CodeChallenge_ Effects of mini-batch size.en.srt |
18.09Кб |
| 012 CodeChallenge_ Effects of mini-batch size.mp4 |
95.42Мб |
| 012 Creating and using custom DataLoaders.en.srt |
26.50Кб |
| 012 Creating and using custom DataLoaders.mp4 |
139.53Мб |
| 012 Mean and variance.en.srt |
22.48Кб |
| 012 Mean and variance.mp4 |
80.57Мб |
| 012 The EMNIST dataset (letter recognition).en.srt |
36.14Кб |
| 012 The EMNIST dataset (letter recognition).mp4 |
201.31Мб |
| 012 Universal approximation theorem.en.srt |
11.70Кб |
| 012 Universal approximation theorem.mp4 |
49.18Мб |
| 012 Why multilayer linear models don't exist.en.srt |
9.21Кб |
| 012 Why multilayer linear models don't exist.mp4 |
26.46Мб |
| 013 CodeChallenge_ Predict sugar.en.srt |
24.98Кб |
| 013 CodeChallenge_ Predict sugar.mp4 |
122.10Мб |
| 013 Dropout in CNNs.en.srt |
14.17Кб |
| 013 Dropout in CNNs.mp4 |
82.73Мб |
| 013 Multi-output ANN (iris dataset).en.srt |
37.47Кб |
| 013 Multi-output ANN (iris dataset).mp4 |
186.77Мб |
| 013 Random sampling and sampling variability.en.srt |
16.36Кб |
| 013 Random sampling and sampling variability.mp4 |
85.42Мб |
| 014 CodeChallenge_ How low can you go_.en.srt |
9.95Кб |
| 014 CodeChallenge_ How low can you go_.mp4 |
55.36Мб |
| 014 CodeChallenge_ more qwerties!.en.srt |
17.79Кб |
| 014 CodeChallenge_ more qwerties!.mp4 |
95.10Мб |
| 014 Loss functions.en.srt |
24.18Кб |
| 014 Loss functions.mp4 |
90.30Мб |
| 014 Reproducible randomness via seeding.en.srt |
11.76Кб |
| 014 Reproducible randomness via seeding.mp4 |
69.70Мб |
| 015 CodeChallenge_ Varying number of channels.en.srt |
19.61Кб |
| 015 CodeChallenge_ Varying number of channels.mp4 |
92.37Мб |
| 015 Comparing the number of hidden units.en.srt |
14.62Кб |
| 015 Comparing the number of hidden units.mp4 |
71.15Мб |
| 015 Loss functions in PyTorch.en.srt |
26.87Кб |
| 015 Loss functions in PyTorch.mp4 |
138.10Мб |
| 015 The t-test.en.srt |
19.38Кб |
| 015 The t-test.mp4 |
81.36Мб |
| 016 Depth vs. breadth_ number of parameters.en.srt |
25.73Кб |
| 016 Depth vs. breadth_ number of parameters.mp4 |
132.07Мб |
| 016 Derivatives_ intuition and polynomials.en.srt |
24.42Кб |
| 016 Derivatives_ intuition and polynomials.mp4 |
80.30Мб |
| 016 More practice with multioutput ANNs.en.srt |
20.32Кб |
| 016 More practice with multioutput ANNs.mp4 |
99.80Мб |
| 016 So many possibilities! How to create a CNN_.en.srt |
6.51Кб |
| 016 So many possibilities! How to create a CNN_.mp4 |
21.04Мб |
| 017 Defining models using sequential vs. class.en.srt |
19.17Кб |
| 017 Defining models using sequential vs. class.mp4 |
89.48Мб |
| 017 Derivatives find minima.en.srt |
12.19Кб |
| 017 Derivatives find minima.mp4 |
45.47Мб |
| 017 Optimizers (minibatch, momentum).mp4 |
98.07Мб |
| 018 Derivatives_ product and chain rules.en.srt |
13.53Кб |
| 018 Derivatives_ product and chain rules.mp4 |
55.63Мб |
| 018 Model depth vs. breadth.en.srt |
30.90Кб |
| 018 Model depth vs. breadth.mp4 |
158.91Мб |
| 018 SGD with momentum.en.srt |
11.58Кб |
| 018 SGD with momentum.mp4 |
62.10Мб |
| 019 CodeChallenge_ convert sequential to class.en.srt |
9.73Кб |
| 019 CodeChallenge_ convert sequential to class.mp4 |
51.44Мб |
| 019 Optimizers (RMSprop, Adam).en.srt |
22.06Кб |
| 019 Optimizers (RMSprop, Adam).mp4 |
76.73Мб |
| 020 Diversity of ANN visual representations.html |
1.40Кб |
| 020 Optimizers comparison.en.srt |
14.64Кб |
| 020 Optimizers comparison.mp4 |
86.88Мб |
| 021 CodeChallenge_ Optimizers and... something.en.srt |
9.36Кб |
| 021 CodeChallenge_ Optimizers and... something.mp4 |
49.77Мб |
| 021 Reflection_ Are DL models understandable yet_.en.srt |
12.37Кб |
| 021 Reflection_ Are DL models understandable yet_.mp4 |
58.59Мб |
| 022 CodeChallenge_ Adam with L2 regularization.en.srt |
10.30Кб |
| 022 CodeChallenge_ Adam with L2 regularization.mp4 |
53.00Мб |
| 023 Learning rate decay.en.srt |
17.91Кб |
| 023 Learning rate decay.mp4 |
96.90Мб |
| 024 How to pick the right metaparameters.en.srt |
16.65Кб |
| 024 How to pick the right metaparameters.mp4 |
61.74Мб |