FreeCourseSite com Udemy - A deep understanding of deep learning with Python intro

1. 01 Introduction/001 How to learn from this course.mp454.97MB
2. 01 Introduction/002 Using Udemy like a pro.mp454.37MB
3. 02 Download all course materials/001 Downloading and using the code.mp445.65MB
4. 02 Download all course materials/002 My policy on code-sharing.mp410.24MB
5. 03 Concepts in deep learning/001 What is an artificial neural network_.mp465.38MB
6. 03 Concepts in deep learning/002 How models _learn_.mp472.79MB
7. 03 Concepts in deep learning/003 The role of DL in science and knowledge.mp4121.55MB
8. 03 Concepts in deep learning/004 Running experiments to understand DL.mp474.84MB
9. 03 Concepts in deep learning/005 Are artificial _neurons_ like biological neurons_.mp4114.65MB
10. 04 About the Python tutorial/001 Should you watch the Python tutorial_.mp423.77MB
11. 05 Math, numpy, PyTorch/001 Introduction to this section.mp411.12MB
12. 05 Math, numpy, PyTorch/002 Spectral theories in mathematics.mp451.06MB
13. 05 Math, numpy, PyTorch/003 Terms and datatypes in math and computers.mp438.08MB
14. 05 Math, numpy, PyTorch/004 Converting reality to numbers.mp433.21MB
15. 05 Math, numpy, PyTorch/005 Vector and matrix transpose.mp437.66MB
16. 05 Math, numpy, PyTorch/006 OMG it's the dot product!.mp450.11MB
17. 05 Math, numpy, PyTorch/007 Matrix multiplication.mp485.67MB
18. 05 Math, numpy, PyTorch/008 Softmax.mp495.96MB
19. 05 Math, numpy, PyTorch/009 Logarithms.mp443.88MB
20. 05 Math, numpy, PyTorch/010 Entropy and cross-entropy.mp4106MB
21. 05 Math, numpy, PyTorch/011 Min_max and argmin_argmax.mp488.21MB
22. 05 Math, numpy, PyTorch/012 Mean and variance.mp480.57MB
23. 05 Math, numpy, PyTorch/013 Random sampling and sampling variability.mp485.42MB
24. 05 Math, numpy, PyTorch/014 Reproducible randomness via seeding.mp469.7MB
25. 05 Math, numpy, PyTorch/015 The t-test.mp481.36MB
26. 05 Math, numpy, PyTorch/016 Derivatives_ intuition and polynomials.mp480.3MB
27. 05 Math, numpy, PyTorch/017 Derivatives find minima.mp445.47MB
28. 05 Math, numpy, PyTorch/018 Derivatives_ product and chain rules.mp455.63MB
29. 06 Gradient descent/001 Overview of gradient descent.mp468.44MB
30. 06 Gradient descent/002 What about local minima_.mp467.08MB
31. 06 Gradient descent/003 Gradient descent in 1D.mp4119.29MB
32. 06 Gradient descent/004 CodeChallenge_ unfortunate starting value.mp477.09MB
33. 06 Gradient descent/005 Gradient descent in 2D.mp495.9MB
34. 06 Gradient descent/006 CodeChallenge_ 2D gradient ascent.mp439.36MB
35. 06 Gradient descent/007 Parametric experiments on g.d.mp4135.61MB
36. 06 Gradient descent/008 CodeChallenge_ fixed vs. dynamic learning rate.mp4114.56MB
37. 06 Gradient descent/009 Vanishing and exploding gradients.mp430.24MB
38. 06 Gradient descent/010 Tangent_ Notebook revision history.mp422.18MB
39. 07 ANNs/001 The perceptron and ANN architecture.mp483.64MB
40. 07 ANNs/002 A geometric view of ANNs.mp470.88MB
41. 07 ANNs/003 ANN math part 1 (forward prop).mp457.9MB
42. 07 ANNs/004 ANN math part 2 (errors, loss, cost).mp448.47MB
43. 07 ANNs/005 ANN math part 3 (backprop).mp452.89MB
44. 07 ANNs/006 ANN for regression.mp4135.5MB
45. 07 ANNs/007 CodeChallenge_ manipulate regression slopes.mp4139.12MB
46. 07 ANNs/008 ANN for classifying qwerties.mp4151.12MB
47. 07 ANNs/009 Learning rates comparison.mp4168.64MB
48. 07 ANNs/010 Multilayer ANN.mp4144.7MB
49. 07 ANNs/011 Linear solutions to linear problems.mp450.37MB
50. 07 ANNs/012 Why multilayer linear models don't exist.mp426.46MB
51. 07 ANNs/013 Multi-output ANN (iris dataset).mp4186.77MB
52. 07 ANNs/014 CodeChallenge_ more qwerties!.mp495.1MB
53. 07 ANNs/015 Comparing the number of hidden units.mp471.15MB
54. 07 ANNs/016 Depth vs. breadth_ number of parameters.mp4132.07MB
55. 07 ANNs/017 Defining models using sequential vs. class.mp489.48MB
56. 07 ANNs/018 Model depth vs. breadth.mp4158.91MB
57. 07 ANNs/019 CodeChallenge_ convert sequential to class.mp451.44MB
58. 07 ANNs/021 Reflection_ Are DL models understandable yet_.mp458.59MB
59. 08 Overfitting and cross-validation/001 What is overfitting and is it as bad as they say_.mp473.13MB
60. 08 Overfitting and cross-validation/002 Cross-validation.mp488.19MB
61. 08 Overfitting and cross-validation/003 Generalization.mp432.44MB
62. 08 Overfitting and cross-validation/004 Cross-validation -- manual separation.mp498.3MB
63. 08 Overfitting and cross-validation/005 Cross-validation -- scikitlearn.mp4142.88MB
64. 08 Overfitting and cross-validation/006 Cross-validation -- DataLoader.mp4172.32MB
65. 08 Overfitting and cross-validation/007 Splitting data into train, devset, test.mp479.21MB
66. 08 Overfitting and cross-validation/008 Cross-validation on regression.mp460.35MB
67. 09 Regularization/001 Regularization_ Concept and methods.mp480.05MB
68. 09 Regularization/002 train() and eval() modes.mp438.34MB
69. 09 Regularization/003 Dropout regularization.mp4136.03MB
70. 09 Regularization/004 Dropout regularization in practice.mp4183.23MB
71. 09 Regularization/005 Dropout example 2.mp453.87MB
72. 09 Regularization/006 Weight regularization (L1_L2)_ math.mp485.41MB
73. 09 Regularization/007 L2 regularization in practice.mp4110.47MB
74. 09 Regularization/008 L1 regularization in practice.mp499.44MB
75. 09 Regularization/009 Training in mini-batches.mp462.12MB
76. 09 Regularization/010 Batch training in action.mp489.1MB
77. 09 Regularization/011 The importance of equal batch sizes.mp460.11MB
78. 09 Regularization/012 CodeChallenge_ Effects of mini-batch size.mp495.42MB
79. 10 Metaparameters (activations, optimizers)/001 What are _metaparameters__.mp432.7MB
80. 10 Metaparameters (activations, optimizers)/002 The _wine quality_ dataset.mp4143.5MB
81. 10 Metaparameters (activations, optimizers)/003 CodeChallenge_ Minibatch size in the wine dataset.mp4118.79MB
82. 10 Metaparameters (activations, optimizers)/004 Data normalization.mp459.81MB
83. 10 Metaparameters (activations, optimizers)/005 The importance of data normalization.mp464.65MB
84. 10 Metaparameters (activations, optimizers)/006 Batch normalization.mp476.81MB
85. 10 Metaparameters (activations, optimizers)/007 Batch normalization in practice.mp461.76MB
86. 10 Metaparameters (activations, optimizers)/008 CodeChallenge_ Batch-normalize the qwerties.mp441.43MB
87. 10 Metaparameters (activations, optimizers)/009 Activation functions.mp497.03MB
88. 10 Metaparameters (activations, optimizers)/010 Activation functions in PyTorch.mp491.46MB
89. 10 Metaparameters (activations, optimizers)/011 Activation functions comparison.mp473.9MB
90. 10 Metaparameters (activations, optimizers)/012 CodeChallenge_ Compare relu variants.mp463.97MB
91. 10 Metaparameters (activations, optimizers)/013 CodeChallenge_ Predict sugar.mp4122.1MB
92. 10 Metaparameters (activations, optimizers)/014 Loss functions.mp490.3MB
93. 10 Metaparameters (activations, optimizers)/015 Loss functions in PyTorch.mp4138.1MB
94. 10 Metaparameters (activations, optimizers)/016 More practice with multioutput ANNs.mp499.8MB
95. 10 Metaparameters (activations, optimizers)/017 Optimizers (minibatch, momentum).mp498.07MB
96. 10 Metaparameters (activations, optimizers)/018 SGD with momentum.mp462.1MB
97. 10 Metaparameters (activations, optimizers)/019 Optimizers (RMSprop, Adam).mp476.73MB
98. 10 Metaparameters (activations, optimizers)/020 Optimizers comparison.mp486.88MB
99. 10 Metaparameters (activations, optimizers)/021 CodeChallenge_ Optimizers and... something.mp449.77MB
100. 10 Metaparameters (activations, optimizers)/022 CodeChallenge_ Adam with L2 regularization.mp453MB
101. 10 Metaparameters (activations, optimizers)/023 Learning rate decay.mp496.9MB
102. 10 Metaparameters (activations, optimizers)/024 How to pick the right metaparameters.mp461.74MB
103. 11 FFNs/001 What are fully-connected and feedforward networks_.mp425.53MB
104. 11 FFNs/002 The MNIST dataset.mp4101.46MB
105. 11 FFNs/003 FFN to classify digits.mp4161.85MB
106. 11 FFNs/004 CodeChallenge_ Binarized MNIST images.mp440.78MB
107. 11 FFNs/005 CodeChallenge_ Data normalization.mp496.25MB
108. 11 FFNs/006 Distributions of weights pre- and post-learning.mp4116.26MB
109. 11 FFNs/007 CodeChallenge_ MNIST and breadth vs. depth.mp495.21MB
110. 11 FFNs/008 CodeChallenge_ Optimizers and MNIST.mp446.26MB
111. 11 FFNs/009 Scrambled MNIST.mp460.17MB
112. 11 FFNs/010 Shifted MNIST.mp477.91MB
113. 11 FFNs/011 CodeChallenge_ The mystery of the missing 7.mp474.25MB
114. 11 FFNs/012 Universal approximation theorem.mp449.18MB
115. 12 More on data/001 Anatomy of a torch dataset and dataloader.mp4135.84MB
116. 12 More on data/002 Data size and network size.mp4135.67MB
117. 12 More on data/003 CodeChallenge_ unbalanced data.mp4166.26MB
118. 12 More on data/004 What to do about unbalanced designs_.mp454.21MB
119. 12 More on data/005 Data oversampling in MNIST.mp4122.59MB
120. 12 More on data/006 Data noise augmentation (with devset+test).mp4106.09MB
121. 12 More on data/007 Data feature augmentation.mp4158.27MB
122. 12 More on data/008 Getting data into colab.mp443.75MB
123. 12 More on data/009 Save and load trained models.mp455.71MB
124. 12 More on data/010 Save the best-performing model.mp4126.5MB
125. 12 More on data/011 Where to find online datasets.mp441.7MB
126. 13 Measuring model performance/001 Two perspectives of the world.mp440.01MB
127. 13 Measuring model performance/002 Accuracy, precision, recall, F1.mp472.57MB
128. 13 Measuring model performance/003 APRF in code.mp451.79MB
129. 13 Measuring model performance/004 APRF example 1_ wine quality.mp4107.35MB
130. 13 Measuring model performance/005 APRF example 2_ MNIST.mp498.62MB
131. 13 Measuring model performance/006 CodeChallenge_ MNIST with unequal groups.mp462.37MB
132. 13 Measuring model performance/007 Computation time.mp481.73MB
133. 13 Measuring model performance/008 Better performance in test than train_.mp444.83MB
134. 14 FFN milestone projects/001 Project 1_ A gratuitously complex adding machine.mp448.55MB
135. 14 FFN milestone projects/002 Project 1_ My solution.mp499.75MB
136. 14 FFN milestone projects/003 Project 2_ Predicting heart disease.mp450.61MB
137. 14 FFN milestone projects/004 Project 2_ My solution.mp4155.73MB
138. 14 FFN milestone projects/005 Project 3_ FFN for missing data interpolation.mp445.39MB
139. 14 FFN milestone projects/006 Project 3_ My solution.mp475.48MB
140. 15 Weight inits and investigations/001 Explanation of weight matrix sizes.mp468.98MB
141. 15 Weight inits and investigations/002 A surprising demo of weight initializations.mp4121.57MB
142. 15 Weight inits and investigations/003 Theory_ Why and how to initialize weights.mp479.41MB
143. 15 Weight inits and investigations/004 CodeChallenge_ Weight variance inits.mp4103.96MB
144. 15 Weight inits and investigations/005 Xavier and Kaiming initializations.mp4134.08MB
145. 15 Weight inits and investigations/006 CodeChallenge_ Xavier vs. Kaiming.mp4126.5MB
146. 15 Weight inits and investigations/007 CodeChallenge_ Identically random weights.mp488.17MB
147. 15 Weight inits and investigations/008 Freezing weights during learning.mp493.15MB
148. 15 Weight inits and investigations/009 Learning-related changes in weights.mp4146.78MB
149. 15 Weight inits and investigations/010 Use default inits or apply your own_.mp428.05MB
150. 16 Autoencoders/001 What are autoencoders and what do they do_.mp449.04MB
151. 16 Autoencoders/002 Denoising MNIST.mp4118.53MB
152. 16 Autoencoders/003 CodeChallenge_ How many units_.mp4135.38MB
153. 16 Autoencoders/004 AEs for occlusion.mp4138.2MB
154. 16 Autoencoders/005 The latent code of MNIST.mp4161.81MB
155. 16 Autoencoders/006 Autoencoder with tied weights.mp4177.74MB
156. 17 Running models on a GPU/001 What is a GPU and why use it_.mp488.73MB
157. 17 Running models on a GPU/002 Implementation.mp476.6MB
158. 17 Running models on a GPU/003 CodeChallenge_ Run an experiment on the GPU.mp452.99MB
159. 18 Convolution and transformations/001 Convolution_ concepts.mp498.06MB
160. 18 Convolution and transformations/002 Feature maps and convolution kernels.mp470.41MB
161. 18 Convolution and transformations/003 Convolution in code.mp4173.1MB
162. 18 Convolution and transformations/004 Convolution parameters (stride, padding).mp466.93MB
163. 18 Convolution and transformations/005 The Conv2 class in PyTorch.mp4100.19MB
164. 18 Convolution and transformations/006 CodeChallenge_ Choose the parameters.mp458.71MB
165. 18 Convolution and transformations/007 Transpose convolution.mp492.89MB
166. 18 Convolution and transformations/008 Max_mean pooling.mp489.07MB
167. 18 Convolution and transformations/009 Pooling in PyTorch.mp481.02MB
168. 18 Convolution and transformations/010 To pool or to stride_.mp455.51MB
169. 18 Convolution and transformations/011 Image transforms.mp4129.9MB
170. 18 Convolution and transformations/012 Creating and using custom DataLoaders.mp4139.53MB
171. 19 Understand and design CNNs/001 The canonical CNN architecture.mp455.83MB
172. 19 Understand and design CNNs/002 CNN to classify MNIST digits.mp4200.33MB
173. 19 Understand and design CNNs/003 CNN on shifted MNIST.mp458.34MB
174. 19 Understand and design CNNs/004 Classify Gaussian blurs.mp4185.14MB
175. 19 Understand and design CNNs/005 Examine feature map activations.mp4260.56MB
176. 19 Understand and design CNNs/006 CodeChallenge_ Softcode internal parameters.mp4120.1MB
177. 19 Understand and design CNNs/007 CodeChallenge_ How wide the FC_.mp494.08MB
178. 19 Understand and design CNNs/008 Do autoencoders clean Gaussians_.mp4147.88MB
179. 19 Understand and design CNNs/009 CodeChallenge_ AEs and occluded Gaussians.mp489.45MB
180. 19 Understand and design CNNs/010 CodeChallenge_ Custom loss functions.mp4132.89MB
181. 19 Understand and design CNNs/011 Discover the Gaussian parameters.mp4136.65MB
182. 19 Understand and design CNNs/012 The EMNIST dataset (letter recognition).mp4201.31MB
183. 19 Understand and design CNNs/013 Dropout in CNNs.mp482.73MB
184. 19 Understand and design CNNs/014 CodeChallenge_ How low can you go_.mp455.36MB
185. 19 Understand and design CNNs/015 CodeChallenge_ Varying number of channels.mp492.37MB
186. 19 Understand and design CNNs/016 So many possibilities! How to create a CNN_.mp421.04MB
187. 20 CNN milestone projects/001 Project 1_ Import and classify CIFAR10.mp448.36MB
188. 20 CNN milestone projects/002 Project 1_ My solution.mp4118.6MB
189. 20 CNN milestone projects/003 Project 2_ CIFAR-autoencoder.mp433.37MB
190. 20 CNN milestone projects/004 Project 3_ FMNIST.mp426.45MB
191. 20 CNN milestone projects/005 Project 4_ Psychometric functions in CNNs.mp476.27MB
192. 21 Transfer learning/001 Transfer learning_ What, why, and when_.mp496.61MB
193. 21 Transfer learning/002 Transfer learning_ MNIST -_ FMNIST.mp490.35MB
194. 21 Transfer learning/003 CodeChallenge_ letters to numbers.mp4118.74MB
195. 21 Transfer learning/004 Famous CNN architectures.mp441.28MB
196. 21 Transfer learning/005 Transfer learning with ResNet-18.mp4148.46MB
197. 21 Transfer learning/006 CodeChallenge_ VGG-16.mp420.28MB
198. 21 Transfer learning/007 Pretraining with autoencoders.mp4156.58MB
199. 21 Transfer learning/008 CIFAR10 with autoencoder-pretrained model.mp4153.34MB
200. 22 Style transfer/001 What is style transfer and how does it work_.mp440.57MB
201. 22 Style transfer/002 The Gram matrix (feature activation covariance).mp466.49MB
202. 22 Style transfer/003 The style transfer algorithm.mp467.31MB
203. 22 Style transfer/004 Transferring the screaming bathtub.mp4216.82MB
204. 22 Style transfer/005 CodeChallenge_ Style transfer with AlexNet.mp453.47MB
205. 23 Generative adversarial networks/001 GAN_ What, why, and how.mp489.74MB
206. 23 Generative adversarial networks/002 Linear GAN with MNIST.mp4169.9MB
207. 23 Generative adversarial networks/003 CodeChallenge_ Linear GAN with FMNIST.mp462.73MB
208. 23 Generative adversarial networks/004 CNN GAN with Gaussians.mp4135.7MB
209. 23 Generative adversarial networks/005 CodeChallenge_ Gaussians with fewer layers.mp453.06MB
210. 23 Generative adversarial networks/006 CNN GAN with FMNIST.mp454.58MB
211. 23 Generative adversarial networks/007 CodeChallenge_ CNN GAN with CIFAR.mp460.77MB
212. 24 Ethics of deep learning/001 Will AI save us or destroy us_.mp465.92MB
213. 24 Ethics of deep learning/002 Example case studies.mp452.92MB
214. 24 Ethics of deep learning/003 Some other possible ethical scenarios.mp466.25MB
215. 24 Ethics of deep learning/004 Will deep learning take our jobs_.mp475.14MB
216. 24 Ethics of deep learning/005 Accountability and making ethical AI.mp470.06MB
217. 25 Where to go from here_/001 How to learn topic _X_ in deep learning_.mp442.03MB
218. 25 Where to go from here_/002 How to read academic DL papers.mp4141.85MB
219. 27 Python intro_ Data types/001 How to learn from the Python tutorial.mp421.97MB
220. 27 Python intro_ Data types/002 Variables.mp477.58MB
221. 27 Python intro_ Data types/003 Math and printing.mp478.5MB
222. 27 Python intro_ Data types/004 Lists (1 of 2).mp455.04MB
223. 27 Python intro_ Data types/005 Lists (2 of 2).mp446.69MB
224. 27 Python intro_ Data types/006 Tuples.mp435.75MB
225. 27 Python intro_ Data types/007 Booleans.mp476.83MB
226. 27 Python intro_ Data types/008 Dictionaries.mp450.67MB
227. 28 Python intro_ Indexing, slicing/001 Indexing.mp451.07MB
228. 28 Python intro_ Indexing, slicing/002 Slicing.mp448.45MB
229. 29 Python intro_ Functions/001 Inputs and outputs.mp429.49MB
230. 29 Python intro_ Functions/002 Python libraries (numpy).mp463.39MB
231. 29 Python intro_ Functions/003 Python libraries (pandas).mp481.19MB
232. 29 Python intro_ Functions/004 Getting help on functions.mp448.6MB
233. 29 Python intro_ Functions/005 Creating functions.mp488.43MB
234. 29 Python intro_ Functions/006 Global and local variable scopes.mp465.96MB
235. 29 Python intro_ Functions/007 Copies and referents of variables.mp423.78MB
236. 29 Python intro_ Functions/008 Classes and object-oriented programming.mp4108.18MB
237. 30 Python intro_ Flow control/001 If-else statements.mp466.8MB
238. 30 Python intro_ Flow control/002 If-else statements, part 2.mp491.12MB
239. 30 Python intro_ Flow control/003 For loops.mp487.13MB
240. 30 Python intro_ Flow control/004 Enumerate and zip.mp458.59MB
241. 30 Python intro_ Flow control/005 Continue.mp433.03MB
242. 30 Python intro_ Flow control/006 Initializing variables.mp491.05MB
243. 30 Python intro_ Flow control/007 Single-line loops (list comprehension).mp475.14MB
244. 30 Python intro_ Flow control/008 while loops.mp491.1MB
245. 30 Python intro_ Flow control/009 Broadcasting in numpy.mp471.05MB
246. 30 Python intro_ Flow control/010 Function error checking and handling.mp499.87MB
247. 31 Python intro_ Text and plots/001 Printing and string interpolation.mp494.83MB
248. 31 Python intro_ Text and plots/002 Plotting dots and lines.mp453.87MB
249. 31 Python intro_ Text and plots/003 Subplot geometry.mp486.78MB
250. 31 Python intro_ Text and plots/004 Making the graphs look nicer.mp4107.66MB
251. 31 Python intro_ Text and plots/005 Seaborn.mp459.72MB
252. 31 Python intro_ Text and plots/006 Images.mp493.56MB
253. 31 Python intro_ Text and plots/007 Export plots in low and high resolution.mp443.57MB