|
Please note that this page does not hosts or makes available any of the listed filenames. You
cannot download any of those files from here.
|
| [CourseClub.Me].url |
122B |
| [CourseClub.Me].url |
122B |
| [CourseClub.Me].url |
122B |
| [CourseClub.Me].url |
122B |
| [CourseClub.Me].url |
122B |
| [CourseClub.Me].url |
122B |
| [CourseClub.ME].url |
122B |
| [GigaCourse.Com].url |
49B |
| [GigaCourse.Com].url |
49B |
| [GigaCourse.Com].url |
49B |
| [GigaCourse.Com].url |
49B |
| [GigaCourse.Com].url |
49B |
| [GigaCourse.Com].url |
49B |
| [GigaCourse.Com].url |
49B |
| 001 Anatomy of a torch dataset and dataloader_en.srt |
25.42KB |
| 001 Anatomy of a torch dataset and dataloader.mp4 |
135.84MB |
| 001 Bonus content.html |
3.64KB |
| 001 Convolution concepts_en.srt |
31.18KB |
| 001 Convolution concepts.mp4 |
97.99MB |
| 001 Downloading and using the code_en.srt |
9.06KB |
| 001 Downloading and using the code.mp4 |
45.65MB |
| 001 DUDL-PythonCode.zip |
660.79KB |
| 001 Explanation of weight matrix sizes_en.srt |
16.55KB |
| 001 Explanation of weight matrix sizes.mp4 |
68.98MB |
| 001 GAN What, why, and how_en.srt |
22.67KB |
| 001 GAN What, why, and how.mp4 |
89.74MB |
| 001 How to learn from the Python tutorial_en.srt |
4.67KB |
| 001 How to learn from the Python tutorial.mp4 |
21.97MB |
| 001 How to learn from this course_en.srt |
12.48KB |
| 001 How to learn from this course.mp4 |
54.97MB |
| 001 How to learn topic _X_ in deep learning_en.srt |
11.88KB |
| 001 How to learn topic _X_ in deep learning.mp4 |
42.03MB |
| 001 If-else statements_en.srt |
20.84KB |
| 001 If-else statements.mp4 |
66.80MB |
| 001 Indexing_en.srt |
17.40KB |
| 001 Indexing.mp4 |
51.07MB |
| 001 Inputs and outputs_en.srt |
10.16KB |
| 001 Inputs and outputs.mp4 |
29.49MB |
| 001 Leveraging sequences in deep learning_en.srt |
18.13KB |
| 001 Leveraging sequences in deep learning.mp4 |
72.79MB |
| 001 Overview of gradient descent_en.srt |
20.10KB |
| 001 Overview of gradient descent.mp4 |
68.44MB |
| 001 Printing and string interpolation_en.srt |
23.41KB |
| 001 Printing and string interpolation.mp4 |
94.83MB |
| 001 Project 1 A gratuitously complex adding machine_en.srt |
10.33KB |
| 001 Project 1 A gratuitously complex adding machine.mp4 |
48.55MB |
| 001 Project 1 Import and classify CIFAR10_en.srt |
10.17KB |
| 001 Project 1 Import and classify CIFAR10.mp4 |
48.36MB |
| 001 PyTorch or TensorFlow.html |
1.07KB |
| 001 Regularization Concept and methods_en.srt |
18.35KB |
| 001 Regularization Concept and methods.mp4 |
80.05MB |
| 001 Should you watch the Python tutorial_en.srt |
5.92KB |
| 001 Should you watch the Python tutorial.mp4 |
23.77MB |
| 001 The canonical CNN architecture_en.srt |
15.12KB |
| 001 The canonical CNN architecture.mp4 |
55.83MB |
| 001 The perceptron and ANN architecture_en.srt |
26.89KB |
| 001 The perceptron and ANN architecture.mp4 |
85.84MB |
| 001 Transfer learning What, why, and when_en.srt |
23.86KB |
| 001 Transfer learning What, why, and when.mp4 |
96.61MB |
| 001 Two perspectives of the world_en.srt |
9.91KB |
| 001 Two perspectives of the world.mp4 |
40.01MB |
| 001 What are autoencoders and what do they do_en.srt |
16.30KB |
| 001 What are autoencoders and what do they do.mp4 |
49.04MB |
| 001 What are fully-connected and feedforward networks_en.srt |
6.70KB |
| 001 What are fully-connected and feedforward networks.mp4 |
25.53MB |
| 001 What are metaparameters_en.srt |
7.09KB |
| 001 What are metaparameters.mp4 |
32.70MB |
| 001 What is a GPU and why use it_en.srt |
21.62KB |
| 001 What is a GPU and why use it.mp4 |
88.73MB |
| 001 What is an artificial neural network_en.srt |
20.55KB |
| 001 What is an artificial neural network.mp4 |
65.38MB |
| 001 What is overfitting and is it as bad as they say_en.srt |
17.66KB |
| 001 What is overfitting and is it as bad as they say.mp4 |
73.13MB |
| 001 What is style transfer and how does it work_en.srt |
6.11KB |
| 001 What is style transfer and how does it work.mp4 |
40.57MB |
| 001 Will AI save us or destroy us_en.srt |
13.83KB |
| 001 Will AI save us or destroy us.mp4 |
65.92MB |
| 002 Accuracy, precision, recall, F1_en.srt |
17.32KB |
| 002 Accuracy, precision, recall, F1.mp4 |
72.58MB |
| 002 A geometric view of ANNs_en.srt |
18.65KB |
| 002 A geometric view of ANNs.mp4 |
70.88MB |
| 002 A surprising demo of weight initializations_en.srt |
23.00KB |
| 002 A surprising demo of weight initializations.mp4 |
121.57MB |
| 002 CNN to classify MNIST digits_en.srt |
36.60KB |
| 002 CNN to classify MNIST digits.mp4 |
200.33MB |
| 002 Cross-validation_en.srt |
24.05KB |
| 002 Cross-validation.mp4 |
88.19MB |
| 002 Data size and network size_en.srt |
22.54KB |
| 002 Data size and network size.mp4 |
135.67MB |
| 002 Denoising MNIST_en.srt |
21.93KB |
| 002 Denoising MNIST.mp4 |
118.53MB |
| 002 Example case studies_en.srt |
8.83KB |
| 002 Example case studies.mp4 |
52.92MB |
| 002 Feature maps and convolution kernels_en.srt |
13.45KB |
| 002 Feature maps and convolution kernels.mp4 |
70.41MB |
| 002 How models learn_en.srt |
18.07KB |
| 002 How models learn.mp4 |
72.79MB |
| 002 How RNNs work_en.srt |
20.96KB |
| 002 How RNNs work.mp4 |
74.85MB |
| 002 How to read academic DL papers_en.srt |
24.46KB |
| 002 How to read academic DL papers.mp4 |
141.85MB |
| 002 If-else statements, part 2_en.srt |
22.02KB |
| 002 If-else statements, part 2.mp4 |
91.12MB |
| 002 Implementation_en.srt |
14.24KB |
| 002 Implementation.mp4 |
76.60MB |
| 002 Introduction to this section_en.srt |
2.80KB |
| 002 Introduction to this section.mp4 |
11.12MB |
| 002 Linear GAN with MNIST_en.srt |
30.76KB |
| 002 Linear GAN with MNIST.mp4 |
169.90MB |
| 002 My policy on code-sharing_en.srt |
2.43KB |
| 002 My policy on code-sharing.mp4 |
10.24MB |
| 002 Plotting dots and lines_en.srt |
17.02KB |
| 002 Plotting dots and lines.mp4 |
53.87MB |
| 002 Project 1 My solution_en.srt |
16.30KB |
| 002 Project 1 My solution_en.srt |
16.52KB |
| 002 Project 1 My solution.mp4 |
99.75MB |
| 002 Project 1 My solution.mp4 |
118.60MB |
| 002 Python libraries (numpy)_en.srt |
19.26KB |
| 002 Python libraries (numpy).mp4 |
63.39MB |
| 002 Slicing_en.srt |
17.26KB |
| 002 Slicing.mp4 |
48.45MB |
| 002 The Gram matrix (feature activation covariance)_en.srt |
16.19KB |
| 002 The Gram matrix (feature activation covariance).mp4 |
66.49MB |
| 002 The MNIST dataset_en.srt |
17.70KB |
| 002 The MNIST dataset.mp4 |
101.38MB |
| 002 The wine quality dataset_en.srt |
24.77KB |
| 002 The wine quality dataset.mp4 |
143.50MB |
| 002 train() and eval() modes_en.srt |
9.82KB |
| 002 train() and eval() modes.mp4 |
38.34MB |
| 002 Transfer learning MNIST - FMNIST_en.srt |
14.02KB |
| 002 Transfer learning MNIST - FMNIST.mp4 |
90.35MB |
| 002 Using Udemy like a pro_en.srt |
11.84KB |
| 002 Using Udemy like a pro.mp4 |
54.37MB |
| 002 Variables_en.srt |
26.21KB |
| 002 Variables.mp4 |
77.58MB |
| 002 What about local minima_en.srt |
16.54KB |
| 002 What about local minima.mp4 |
67.08MB |
| 003 ANN math part 1 (forward prop)_en.srt |
21.38KB |
| 003 ANN math part 1 (forward prop).mp4 |
73.12MB |
| 003 APRF in code_en.srt |
9.03KB |
| 003 APRF in code.mp4 |
51.79MB |
| 003 CNN on shifted MNIST_en.srt |
11.66KB |
| 003 CNN on shifted MNIST.mp4 |
58.34MB |
| 003 CodeChallenge How many units_en.srt |
27.80KB |
| 003 CodeChallenge How many units.mp4 |
135.38MB |
| 003 CodeChallenge letters to numbers_en.srt |
19.77KB |
| 003 CodeChallenge letters to numbers.mp4 |
118.74MB |
| 003 CodeChallenge Linear GAN with FMNIST_en.srt |
13.38KB |
| 003 CodeChallenge Linear GAN with FMNIST.mp4 |
62.73MB |
| 003 CodeChallenge Minibatch size in the wine dataset_en.srt |
22.22KB |
| 003 CodeChallenge Minibatch size in the wine dataset.mp4 |
118.79MB |
| 003 CodeChallenge Run an experiment on the GPU_en.srt |
9.43KB |
| 003 CodeChallenge Run an experiment on the GPU.mp4 |
52.99MB |
| 003 CodeChallenge unbalanced data_en.srt |
28.21KB |
| 003 CodeChallenge unbalanced data.mp4 |
166.26MB |
| 003 Convolution in code_en.srt |
29.39KB |
| 003 Convolution in code.mp4 |
173.10MB |
| 003 Dropout regularization_en.srt |
30.42KB |
| 003 Dropout regularization.mp4 |
138.39MB |
| 003 FFN to classify digits_en.srt |
31.66KB |
| 003 FFN to classify digits.mp4 |
161.85MB |
| 003 For loops_en.srt |
24.28KB |
| 003 For loops.mp4 |
87.13MB |
| 003 Generalization_en.srt |
8.50KB |
| 003 Generalization.mp4 |
32.44MB |
| 003 Gradient descent in 1D_en.srt |
23.78KB |
| 003 Gradient descent in 1D.mp4 |
119.29MB |
| 003 Math and printing_en.srt |
25.73KB |
| 003 Math and printing.mp4 |
78.50MB |
| 003 Project 2 CIFAR-autoencoder_en.srt |
6.75KB |
| 003 Project 2 CIFAR-autoencoder.mp4 |
33.37MB |
| 003 Project 2 Predicting heart disease_en.srt |
10.57KB |
| 003 Project 2 Predicting heart disease.mp4 |
50.61MB |
| 003 Python libraries (pandas)_en.srt |
19.51KB |
| 003 Python libraries (pandas).mp4 |
81.19MB |
| 003 Some other possible ethical scenarios_en.srt |
14.65KB |
| 003 Some other possible ethical scenarios.mp4 |
66.25MB |
| 003 Spectral theories in mathematics_en.srt |
13.09KB |
| 003 Spectral theories in mathematics.mp4 |
51.06MB |
| 003 Subplot geometry_en.srt |
22.24KB |
| 003 Subplot geometry.mp4 |
86.78MB |
| 003 Theory Why and how to initialize weights_en.srt |
17.59KB |
| 003 Theory Why and how to initialize weights.mp4 |
79.41MB |
| 003 The RNN class in PyTorch_en.srt |
25.94KB |
| 003 The RNN class in PyTorch.mp4 |
122.98MB |
| 003 The role of DL in science and knowledge_en.srt |
22.48KB |
| 003 The role of DL in science and knowledge.mp4 |
34.76MB |
| 003 The style transfer algorithm_en.srt |
14.54KB |
| 003 The style transfer algorithm.mp4 |
67.31MB |
| 004 AEs for occlusion_en.srt |
24.48KB |
| 004 AEs for occlusion.mp4 |
138.20MB |
| 004 ANN math part 2 (errors, loss, cost)_en.srt |
13.39KB |
| 004 ANN math part 2 (errors, loss, cost).mp4 |
48.47MB |
| 004 APRF example 1 wine quality_en.srt |
18.52KB |
| 004 APRF example 1 wine quality.mp4 |
107.35MB |
| 004 Classify Gaussian blurs_en.srt |
33.00KB |
| 004 Classify Gaussian blurs.mp4 |
185.14MB |
| 004 CNN GAN with Gaussians_en.srt |
21.29KB |
| 004 CNN GAN with Gaussians.mp4 |
135.70MB |
| 004 CodeChallenge Binarized MNIST images_en.srt |
7.10KB |
| 004 CodeChallenge Binarized MNIST images.mp4 |
40.78MB |
| 004 CodeChallenge unfortunate starting value_en.srt |
15.37KB |
| 004 CodeChallenge unfortunate starting value.mp4 |
77.09MB |
| 004 CodeChallenge Weight variance inits_en.srt |
17.75KB |
| 004 CodeChallenge Weight variance inits.mp4 |
103.96MB |
| 004 Convolution parameters (stride, padding)_en.srt |
17.41KB |
| 004 Convolution parameters (stride, padding).mp4 |
66.93MB |
| 004 Cross-validation -- manual separation_en.srt |
17.89KB |
| 004 Cross-validation -- manual separation.mp4 |
98.30MB |
| 004 Data normalization_en.srt |
18.96KB |
| 004 Data normalization.mp4 |
59.81MB |
| 004 Dropout regularization in practice_en.srt |
32.13KB |
| 004 Dropout regularization in practice.mp4 |
183.23MB |
| 004 Enumerate and zip_en.srt |
15.41KB |
| 004 Enumerate and zip.mp4 |
58.59MB |
| 004 Famous CNN architectures_en.srt |
8.39KB |
| 004 Famous CNN architectures.mp4 |
41.28MB |
| 004 Getting help on functions_en.srt |
10.65KB |
| 004 Getting help on functions.mp4 |
48.60MB |
| 004 Lists (1 of 2)_en.srt |
19.65KB |
| 004 Lists (1 of 2).mp4 |
55.04MB |
| 004 Making the graphs look nicer_en.srt |
25.96KB |
| 004 Making the graphs look nicer.mp4 |
107.66MB |
| 004 Predicting alternating sequences_en.srt |
27.77KB |
| 004 Predicting alternating sequences.mp4 |
160.16MB |
| 004 Project 2 My solution_en.srt |
26.69KB |
| 004 Project 2 My solution.mp4 |
155.73MB |
| 004 Project 3 FMNIST_en.srt |
4.93KB |
| 004 Project 3 FMNIST.mp4 |
26.45MB |
| 004 Running experiments to understand DL_en.srt |
18.53KB |
| 004 Running experiments to understand DL.mp4 |
74.84MB |
| 004 Terms and datatypes in math and computers_en.srt |
10.27KB |
| 004 Terms and datatypes in math and computers.mp4 |
38.08MB |
| 004 Transferring the screaming bathtub_en.srt |
31.05KB |
| 004 Transferring the screaming bathtub.mp4 |
216.82MB |
| 004 What to do about unbalanced designs_en.srt |
10.75KB |
| 004 What to do about unbalanced designs.mp4 |
54.21MB |
| 004 Will deep learning take our jobs_en.srt |
14.35KB |
| 004 Will deep learning take our jobs.mp4 |
75.14MB |
| 005 Accountability and making ethical AI_en.srt |
16.10KB |
| 005 Accountability and making ethical AI.mp4 |
70.06MB |
| 005 ANN math part 3 (backprop)_en.srt |
14.71KB |
| 005 ANN math part 3 (backprop).mp4 |
52.89MB |
| 005 APRF example 2 MNIST_en.srt |
16.52KB |
| 005 APRF example 2 MNIST.mp4 |
98.62MB |
| 005 Are artificial neurons like biological neurons_en.srt |
23.29KB |
| 005 Are artificial neurons like biological neurons.mp4 |
114.65MB |
| 005 CodeChallenge Data normalization_en.srt |
23.57KB |
| 005 CodeChallenge Data normalization.mp4 |
96.25MB |
| 005 CodeChallenge Gaussians with fewer layers_en.srt |
8.61KB |
| 005 CodeChallenge Gaussians with fewer layers.mp4 |
53.06MB |
| 005 CodeChallenge sine wave extrapolation_en.srt |
37.55KB |
| 005 CodeChallenge sine wave extrapolation.mp4 |
195.67MB |
| 005 CodeChallenge Style transfer with AlexNet_en.srt |
10.07KB |
| 005 CodeChallenge Style transfer with AlexNet.mp4 |
53.47MB |
| 005 Continue_en.srt |
9.71KB |
| 005 Continue.mp4 |
33.03MB |
| 005 Converting reality to numbers_en.srt |
9.21KB |
| 005 Converting reality to numbers.mp4 |
33.21MB |
| 005 Creating functions_en.srt |
29.69KB |
| 005 Creating functions.mp4 |
88.43MB |
| 005 Cross-validation -- scikitlearn_en.srt |
29.31KB |
| 005 Cross-validation -- scikitlearn.mp4 |
142.88MB |
| 005 Data oversampling in MNIST_en.srt |
23.24KB |
| 005 Data oversampling in MNIST.mp4 |
122.59MB |
| 005 Dropout example 2_en.srt |
8.83KB |
| 005 Dropout example 2.mp4 |
53.87MB |
| 005 Examine feature map activations_en.srt |
39.00KB |
| 005 Examine feature map activations.mp4 |
260.56MB |
| 005 Gradient descent in 2D_en.srt |
20.74KB |
| 005 Gradient descent in 2D.mp4 |
96.38MB |
| 005 Lists (2 of 2)_en.srt |
14.00KB |
| 005 Lists (2 of 2).mp4 |
46.69MB |
| 005 Project 3 FFN for missing data interpolation_en.srt |
13.85KB |
| 005 Project 3 FFN for missing data interpolation.mp4 |
45.39MB |
| 005 Project 4 Psychometric functions in CNNs_en.srt |
10.74KB |
| 005 Project 4 Psychometric functions in CNNs_en.vtt |
14.22KB |
| 005 Project 4 Psychometric functions in CNNs.mp4 |
76.27MB |
| 005 Seaborn_en.srt |
15.11KB |
| 005 Seaborn.mp4 |
59.72MB |
| 005 The Conv2 class in PyTorch_en.srt |
18.19KB |
| 005 The Conv2 class in PyTorch.mp4 |
100.19MB |
| 005 The importance of data normalization_en.srt |
13.26KB |
| 005 The importance of data normalization.mp4 |
64.65MB |
| 005 The latent code of MNIST_en.srt |
30.47KB |
| 005 The latent code of MNIST.mp4 |
161.81MB |
| 005 Transfer learning with ResNet-18_en.srt |
23.64KB |
| 005 Transfer learning with ResNet-18.mp4 |
148.46MB |
| 005 Xavier and Kaiming initializations_en.srt |
21.70KB |
| 005 Xavier and Kaiming initializations.mp4 |
134.08MB |
| 006 ANN for regression_en.srt |
34.52KB |
| 006 ANN for regression.mp4 |
135.50MB |
| 006 Autoencoder with tied weights_en.srt |
33.51KB |
| 006 Autoencoder with tied weights.mp4 |
177.74MB |
| 006 Batch normalization_en.srt |
18.02KB |
| 006 Batch normalization.mp4 |
76.81MB |
| 006 CNN GAN with FMNIST_en.srt |
8.88KB |
| 006 CNN GAN with FMNIST.mp4 |
54.58MB |
| 006 CodeChallenge 2D gradient ascent_en.srt |
7.24KB |
| 006 CodeChallenge 2D gradient ascent.mp4 |
39.36MB |
| 006 CodeChallenge Choose the parameters_en.srt |
9.75KB |
| 006 CodeChallenge Choose the parameters.mp4 |
58.71MB |
| 006 CodeChallenge MNIST with unequal groups_en.srt |
12.25KB |
| 006 CodeChallenge MNIST with unequal groups.mp4 |
25.07MB |
| 006 CodeChallenge Softcode internal parameters_en.srt |
24.12KB |
| 006 CodeChallenge Softcode internal parameters.mp4 |
120.10MB |
| 006 CodeChallenge VGG-16_en.srt |
4.87KB |
| 006 CodeChallenge VGG-16.mp4 |
20.28MB |
| 006 CodeChallenge Xavier vs. Kaiming_en.srt |
23.71KB |
| 006 CodeChallenge Xavier vs. Kaiming.mp4 |
126.50MB |
| 006 Cross-validation -- DataLoader_en.srt |
27.51KB |
| 006 Cross-validation -- DataLoader.mp4 |
172.32MB |
| 006 Data noise augmentation (with devset+test)_en.srt |
17.93KB |
| 006 Data noise augmentation (with devset+test).mp4 |
106.09MB |
| 006 Distributions of weights pre- and post-learning_en.srt |
21.22KB |
| 006 Distributions of weights pre- and post-learning.mp4 |
116.26MB |
| 006 Global and local variable scopes_en.srt |
18.92KB |
| 006 Global and local variable scopes.mp4 |
65.96MB |
| 006 Images_en.srt |
24.74KB |
| 006 Images.mp4 |
93.56MB |
| 006 Initializing variables_en.srt |
24.64KB |
| 006 Initializing variables.mp4 |
91.05MB |
| 006 More on RNNs Hidden states, embeddings_en.srt |
22.04KB |
| 006 More on RNNs Hidden states, embeddings.mp4 |
29.04MB |
| 006 Project 3 My solution_en.srt |
11.43KB |
| 006 Project 3 My solution.mp4 |
75.48MB |
| 006 Tuples_en.srt |
11.55KB |
| 006 Tuples.mp4 |
35.75MB |
| 006 Vector and matrix transpose_en.srt |
9.63KB |
| 006 Vector and matrix transpose.mp4 |
37.66MB |
| 006 Weight regularization (L1L2) math_en.srt |
26.08KB |
| 006 Weight regularization (L1L2) math.mp4 |
85.41MB |
| 007 Batch normalization in practice_en.srt |
10.64KB |
| 007 Batch normalization in practice.mp4 |
61.76MB |
| 007 Booleans_en.srt |
26.63KB |
| 007 Booleans.mp4 |
76.83MB |
| 007 CodeChallenge CNN GAN with CIFAR_en.srt |
11.22KB |
| 007 CodeChallenge CNN GAN with CIFAR.mp4 |
60.77MB |
| 007 CodeChallenge How wide the FC_en.srt |
15.86KB |
| 007 CodeChallenge How wide the FC.mp4 |
94.08MB |
| 007 CodeChallenge Identically random weights_en.srt |
17.26KB |
| 007 CodeChallenge Identically random weights.mp4 |
88.17MB |
| 007 CodeChallenge manipulate regression slopes_en.srt |
27.25KB |
| 007 CodeChallenge manipulate regression slopes.mp4 |
139.12MB |
| 007 CodeChallenge MNIST and breadth vs. depth_en.srt |
17.09KB |
| 007 CodeChallenge MNIST and breadth vs. depth.mp4 |
95.21MB |
| 007 Computation time_en.srt |
13.73KB |
| 007 Computation time.mp4 |
81.73MB |
| 007 Copies and referents of variables_en.srt |
6.98KB |
| 007 Copies and referents of variables.mp4 |
23.78MB |
| 007 Data feature augmentation_en.srt |
27.30KB |
| 007 Data feature augmentation.mp4 |
158.27MB |
| 007 Export plots in low and high resolution_en.srt |
10.94KB |
| 007 Export plots in low and high resolution.mp4 |
17.17MB |
| 007 GRU and LSTM_en.srt |
32.14KB |
| 007 GRU and LSTM.mp4 |
129.66MB |
| 007 L2 regularization in practice_en.srt |
18.27KB |
| 007 L2 regularization in practice.mp4 |
110.47MB |
| 007 OMG it's the dot product!_en.srt |
13.43KB |
| 007 OMG it's the dot product!.mp4 |
50.11MB |
| 007 Parametric experiments on g.d_en.srt |
26.16KB |
| 007 Parametric experiments on g.d.mp4 |
135.61MB |
| 007 Pretraining with autoencoders_en.srt |
27.70KB |
| 007 Pretraining with autoencoders.mp4 |
156.58MB |
| 007 Single-line loops (list comprehension)_en.srt |
20.91KB |
| 007 Single-line loops (list comprehension).mp4 |
75.14MB |
| 007 Splitting data into train, devset, test_en.srt |
13.31KB |
| 007 Splitting data into train, devset, test.mp4 |
79.21MB |
| 007 Transpose convolution_en.srt |
19.17KB |
| 007 Transpose convolution.mp4 |
92.89MB |
| 008 ANN for classifying qwerties_en.srt |
32.73KB |
| 008 ANN for classifying qwerties.mp4 |
151.12MB |
| 008 Better performance in test than train_en.srt |
11.54KB |
| 008 Better performance in test than train.mp4 |
44.83MB |
| 008 CIFAR10 with autoencoder-pretrained model_en.srt |
24.93KB |
| 008 CIFAR10 with autoencoder-pretrained model.mp4 |
153.34MB |
| 008 Classes and object-oriented programming_en.srt |
25.61KB |
| 008 Classes and object-oriented programming.mp4 |
108.18MB |
| 008 CodeChallenge Batch-normalize the qwerties_en.srt |
7.23KB |
| 008 CodeChallenge Batch-normalize the qwerties.mp4 |
41.43MB |
| 008 CodeChallenge fixed vs. dynamic learning rate_en.srt |
22.55KB |
| 008 CodeChallenge fixed vs. dynamic learning rate.mp4 |
113.60MB |
| 008 CodeChallenge Optimizers and MNIST_en.srt |
9.56KB |
| 008 CodeChallenge Optimizers and MNIST.mp4 |
46.26MB |
| 008 Cross-validation on regression_en.srt |
11.53KB |
| 008 Cross-validation on regression.mp4 |
60.35MB |
| 008 Dictionaries_en.srt |
16.36KB |
| 008 Dictionaries.mp4 |
50.67MB |
| 008 Do autoencoders clean Gaussians_en.srt |
23.50KB |
| 008 Do autoencoders clean Gaussians.mp4 |
147.88MB |
| 008 Freezing weights during learning_en.srt |
18.54KB |
| 008 Freezing weights during learning.mp4 |
93.15MB |
| 008 Getting data into colab_en.srt |
8.52KB |
| 008 Getting data into colab.mp4 |
43.75MB |
| 008 L1 regularization in practice_en.srt |
16.79KB |
| 008 L1 regularization in practice.mp4 |
99.44MB |
| 008 Matrix multiplication_en.srt |
19.84KB |
| 008 Matrix multiplication.mp4 |
85.67MB |
| 008 Maxmean pooling_en.srt |
25.71KB |
| 008 Maxmean pooling.mp4 |
89.07MB |
| 008 The LSTM and GRU classes_en.srt |
19.26KB |
| 008 The LSTM and GRU classes.mp4 |
120.14MB |
| 008 while loops_en.srt |
26.87KB |
| 008 while loops.mp4 |
91.10MB |
| 009 Activation functions_en.srt |
25.53KB |
| 009 Activation functions.mp4 |
97.03MB |
| 009 Broadcasting in numpy_en.srt |
20.52KB |
| 009 Broadcasting in numpy.mp4 |
71.05MB |
| 009 CodeChallenge AEs and occluded Gaussians_en.srt |
13.49KB |
| 009 CodeChallenge AEs and occluded Gaussians.mp4 |
28.58MB |
| 009 Learning rates comparison_en.srt |
34.85KB |
| 009 Learning rates comparison.mp4 |
168.64MB |
| 009 Learning-related changes in weights_en.srt |
31.55KB |
| 009 Learning-related changes in weights.mp4 |
146.78MB |
| 009 Lorem ipsum_en.srt |
35.99KB |
| 009 Lorem ipsum.mp4 |
192.53MB |
| 009 Pooling in PyTorch_en.srt |
18.90KB |
| 009 Pooling in PyTorch.mp4 |
81.02MB |
| 009 Save and load trained models_en.srt |
8.61KB |
| 009 Save and load trained models.mp4 |
55.71MB |
| 009 Scrambled MNIST_en.srt |
10.82KB |
| 009 Scrambled MNIST.mp4 |
60.17MB |
| 009 Softmax_en.srt |
26.74KB |
| 009 Softmax.mp4 |
95.96MB |
| 009 Training in mini-batches_en.srt |
16.24KB |
| 009 Training in mini-batches.mp4 |
62.12MB |
| 009 Vanishing and exploding gradients_en.srt |
8.71KB |
| 009 Vanishing and exploding gradients.mp4 |
30.24MB |
| 010 Activation functions in PyTorch_en.srt |
16.35KB |
| 010 Activation functions in PyTorch.mp4 |
91.46MB |
| 010 Batch training in action_en.srt |
15.06KB |
| 010 Batch training in action.mp4 |
89.10MB |
| 010 CodeChallenge Custom loss functions_en.srt |
28.77KB |
| 010 CodeChallenge Custom loss functions.mp4 |
132.89MB |
| 010 Function error checking and handling_en.srt |
24.39KB |
| 010 Function error checking and handling.mp4 |
99.87MB |
| 010 Logarithms_en.srt |
11.05KB |
| 010 Logarithms.mp4 |
43.88MB |
| 010 Multilayer ANN_en.srt |
28.29KB |
| 010 Multilayer ANN.mp4 |
144.70MB |
| 010 Save the best-performing model_en.srt |
21.15KB |
| 010 Save the best-performing model.mp4 |
126.50MB |
| 010 Shifted MNIST_en.srt |
15.84KB |
| 010 Shifted MNIST.mp4 |
77.91MB |
| 010 Tangent Notebook revision history_en.srt |
2.66KB |
| 010 Tangent Notebook revision history.mp4 |
9.88MB |
| 010 To pool or to stride_en.srt |
13.75KB |
| 010 To pool or to stride.mp4 |
55.51MB |
| 010 Use default inits or apply your own_en.srt |
6.12KB |
| 010 Use default inits or apply your own.mp4 |
28.05MB |
| 011 Activation functions comparison_en.srt |
13.08KB |
| 011 Activation functions comparison.mp4 |
73.90MB |
| 011 CodeChallenge The mystery of the missing 7_en.srt |
15.17KB |
| 011 CodeChallenge The mystery of the missing 7.mp4 |
74.25MB |
| 011 Discover the Gaussian parameters_en.srt |
22.41KB |
| 011 Discover the Gaussian parameters.mp4 |
136.65MB |
| 011 Entropy and cross-entropy_en.srt |
24.46KB |
| 011 Entropy and cross-entropy.mp4 |
106.00MB |
| 011 Image transforms_en.srt |
23.01KB |
| 011 Image transforms.mp4 |
129.90MB |
| 011 Linear solutions to linear problems_en.srt |
11.73KB |
| 011 Linear solutions to linear problems.mp4 |
50.37MB |
| 011 The importance of equal batch sizes_en.srt |
9.12KB |
| 011 The importance of equal batch sizes.mp4 |
60.11MB |
| 011 Where to find online datasets_en.srt |
7.89KB |
| 011 Where to find online datasets.mp4 |
41.70MB |
| 012 CodeChallenge Compare relu variants_en.srt |
10.87KB |
| 012 CodeChallenge Compare relu variants.mp4 |
63.97MB |
| 012 CodeChallenge Effects of mini-batch size_en.srt |
17.42KB |
| 012 CodeChallenge Effects of mini-batch size.mp4 |
95.42MB |
| 012 Creating and using custom DataLoaders_en.srt |
25.50KB |
| 012 Creating and using custom DataLoaders.mp4 |
139.53MB |
| 012 Minmax and argminargmax_en.srt |
17.49KB |
| 012 Minmax and argminargmax.mp4 |
88.21MB |
| 012 The EMNIST dataset (letter recognition)_en.srt |
34.76KB |
| 012 The EMNIST dataset (letter recognition).mp4 |
201.31MB |
| 012 Universal approximation theorem_en.srt |
11.28KB |
| 012 Universal approximation theorem.mp4 |
49.18MB |
| 012 Why multilayer linear models don't exist_en.srt |
8.86KB |
| 012 Why multilayer linear models don't exist.mp4 |
26.46MB |
| 013 CodeChallenge Predict sugar_en.srt |
24.06KB |
| 013 CodeChallenge Predict sugar.mp4 |
122.10MB |
| 013 Dropout in CNNs_en.srt |
13.68KB |
| 013 Dropout in CNNs.mp4 |
82.73MB |
| 013 Mean and variance_en.srt |
21.74KB |
| 013 Mean and variance.mp4 |
81.42MB |
| 013 Multi-output ANN (iris dataset)_en.srt |
36.08KB |
| 013 Multi-output ANN (iris dataset).mp4 |
186.77MB |
| 014 CodeChallenge How low can you go_en.srt |
9.58KB |
| 014 CodeChallenge How low can you go.mp4 |
55.36MB |
| 014 CodeChallenge more qwerties!_en.srt |
17.13KB |
| 014 CodeChallenge more qwerties!.mp4 |
95.10MB |
| 014 Loss functions_en.srt |
23.32KB |
| 014 Loss functions.mp4 |
90.30MB |
| 014 Random sampling and sampling variability_en.srt |
15.75KB |
| 014 Random sampling and sampling variability.mp4 |
85.42MB |
| 015 CodeChallenge Varying number of channels_en.srt |
18.92KB |
| 015 CodeChallenge Varying number of channels.mp4 |
92.37MB |
| 015 Comparing the number of hidden units_en.srt |
14.09KB |
| 015 Comparing the number of hidden units.mp4 |
71.15MB |
| 015 Loss functions in PyTorch_en.srt |
25.85KB |
| 015 Loss functions in PyTorch.mp4 |
138.10MB |
| 015 Reproducible randomness via seeding_en.srt |
11.32KB |
| 015 Reproducible randomness via seeding.mp4 |
69.70MB |
| 016 Depth vs. breadth number of parameters_en.srt |
24.75KB |
| 016 Depth vs. breadth number of parameters.mp4 |
132.07MB |
| 016 More practice with multioutput ANNs_en.srt |
19.57KB |
| 016 More practice with multioutput ANNs.mp4 |
99.80MB |
| 016 So many possibilities! How to create a CNN_en.srt |
6.27KB |
| 016 So many possibilities! How to create a CNN.mp4 |
21.04MB |
| 016 The t-test_en.srt |
18.69KB |
| 016 The t-test.mp4 |
81.36MB |
| 017 Defining models using sequential vs. class_en.srt |
18.45KB |
| 017 Defining models using sequential vs. class.mp4 |
89.48MB |
| 017 Derivatives intuition and polynomials_en.srt |
23.48KB |
| 017 Derivatives intuition and polynomials.mp4 |
80.30MB |
| 017 Optimizers (minibatch, momentum)_en.srt |
26.39KB |
| 017 Optimizers (minibatch, momentum).mp4 |
98.07MB |
| 018 Derivatives find minima_en.srt |
11.71KB |
| 018 Derivatives find minima.mp4 |
45.47MB |
| 018 Model depth vs. breadth_en.srt |
29.73KB |
| 018 Model depth vs. breadth.mp4 |
158.91MB |
| 018 SGD with momentum_en.srt |
11.12KB |
| 018 SGD with momentum.mp4 |
62.10MB |
| 019 CodeChallenge convert sequential to class_en.srt |
9.36KB |
| 019 CodeChallenge convert sequential to class.mp4 |
51.44MB |
| 019 Derivatives product and chain rules_en.srt |
13.04KB |
| 019 Derivatives product and chain rules.mp4 |
55.63MB |
| 019 Optimizers (RMSprop, Adam)_en.srt |
21.25KB |
| 019 Optimizers (RMSprop, Adam).mp4 |
76.73MB |
| 020 Diversity of ANN visual representations.html |
517B |
| 020 Optimizers comparison_en.srt |
14.10KB |
| 020 Optimizers comparison.mp4 |
86.88MB |
| 021 CodeChallenge Optimizers and... something_en.srt |
9.03KB |
| 021 CodeChallenge Optimizers and... something.mp4 |
49.77MB |
| 021 Reflection Are DL models understandable yet_en.srt |
11.95KB |
| 021 Reflection Are DL models understandable yet.mp4 |
58.59MB |
| 022 CodeChallenge Adam with L2 regularization_en.srt |
9.94KB |
| 022 CodeChallenge Adam with L2 regularization.mp4 |
53.00MB |
| 023 Learning rate decay_en.srt |
17.23KB |
| 023 Learning rate decay.mp4 |
96.90MB |
| 024 How to pick the right metaparameters_en.srt |
16.08KB |
| 024 How to pick the right metaparameters.mp4 |
61.74MB |