[] Udemy - A deep understanding of deep learning (with Python intro)

收录时间:2022-01-19 15:58:31
文件大小:21GB
下载次数:1
最近下载:2022-01-19 15:58:31
磁力链接:
magnet:?xt=urn:btih:6b21398f8f633ecfb7921fd4832dcfbecaeb17f0

立即下载 复制链接

文件列表

19 Understand and design CNNs/005 Examine feature map activations.mp4 261MB
22 Style transfer/004 Transferring the screaming bathtub.mp4 217MB
19 Understand and design CNNs/012 The EMNIST dataset (letter recognition).mp4 201MB
19 Understand and design CNNs/002 CNN to classify MNIST digits.mp4 200MB
07 ANNs/013 Multi-output ANN (iris dataset).mp4 187MB
19 Understand and design CNNs/004 Classify Gaussian blurs.mp4 185MB
09 Regularization/004 Dropout regularization in practice.mp4 183MB
16 Autoencoders/006 Autoencoder with tied weights.mp4 178MB
18 Convolution and transformations/003 Convolution in code.mp4 173MB
08 Overfitting and cross-validation/006 Cross-validation -- DataLoader.mp4 172MB
23 Generative adversarial networks/002 Linear GAN with MNIST.mp4 170MB
07 ANNs/009 Learning rates comparison.mp4 169MB
12 More on data/003 CodeChallenge_ unbalanced data.mp4 166MB
11 FFNs/003 FFN to classify digits.mp4 162MB
16 Autoencoders/005 The latent code of MNIST.mp4 162MB
07 ANNs/018 Model depth vs. breadth.mp4 159MB
12 More on data/007 Data feature augmentation.mp4 158MB
21 Transfer learning/007 Pretraining with autoencoders.mp4 157MB
14 FFN milestone projects/004 Project 2_ My solution.mp4 156MB
21 Transfer learning/008 CIFAR10 with autoencoder-pretrained model.mp4 153MB
07 ANNs/008 ANN for classifying qwerties.mp4 151MB
21 Transfer learning/005 Transfer learning with ResNet-18.mp4 148MB
19 Understand and design CNNs/008 Do autoencoders clean Gaussians_.mp4 148MB
15 Weight inits and investigations/009 Learning-related changes in weights.mp4 147MB
07 ANNs/010 Multilayer ANN.mp4 145MB
10 Metaparameters (activations, optimizers)/002 The _wine quality_ dataset.mp4 143MB
08 Overfitting and cross-validation/005 Cross-validation -- scikitlearn.mp4 143MB
25 Where to go from here_/002 How to read academic DL papers.mp4 142MB
18 Convolution and transformations/012 Creating and using custom DataLoaders.mp4 140MB
07 ANNs/007 CodeChallenge_ manipulate regression slopes.mp4 139MB
16 Autoencoders/004 AEs for occlusion.mp4 138MB
10 Metaparameters (activations, optimizers)/015 Loss functions in PyTorch.mp4 138MB
19 Understand and design CNNs/011 Discover the Gaussian parameters.mp4 137MB
09 Regularization/003 Dropout regularization.mp4 136MB
12 More on data/001 Anatomy of a torch dataset and dataloader.mp4 136MB
23 Generative adversarial networks/004 CNN GAN with Gaussians.mp4 136MB
12 More on data/002 Data size and network size.mp4 136MB
06 Gradient descent/007 Parametric experiments on g.d.mp4 136MB
07 ANNs/006 ANN for regression.mp4 136MB
16 Autoencoders/003 CodeChallenge_ How many units_.mp4 135MB
15 Weight inits and investigations/005 Xavier and Kaiming initializations.mp4 134MB
19 Understand and design CNNs/010 CodeChallenge_ Custom loss functions.mp4 133MB
07 ANNs/016 Depth vs. breadth_ number of parameters.mp4 132MB
18 Convolution and transformations/011 Image transforms.mp4 130MB
15 Weight inits and investigations/006 CodeChallenge_ Xavier vs. Kaiming.mp4 127MB
12 More on data/010 Save the best-performing model.mp4 127MB
12 More on data/005 Data oversampling in MNIST.mp4 123MB
10 Metaparameters (activations, optimizers)/013 CodeChallenge_ Predict sugar.mp4 122MB
15 Weight inits and investigations/002 A surprising demo of weight initializations.mp4 122MB
03 Concepts in deep learning/003 The role of DL in science and knowledge.mp4 122MB
19 Understand and design CNNs/006 CodeChallenge_ Softcode internal parameters.mp4 120MB
06 Gradient descent/003 Gradient descent in 1D.mp4 119MB
10 Metaparameters (activations, optimizers)/003 CodeChallenge_ Minibatch size in the wine dataset.mp4 119MB
21 Transfer learning/003 CodeChallenge_ letters to numbers.mp4 119MB
20 CNN milestone projects/002 Project 1_ My solution.mp4 119MB
16 Autoencoders/002 Denoising MNIST.mp4 119MB
11 FFNs/006 Distributions of weights pre- and post-learning.mp4 116MB
03 Concepts in deep learning/005 Are artificial _neurons_ like biological neurons_.mp4 115MB
06 Gradient descent/008 CodeChallenge_ fixed vs. dynamic learning rate.mp4 115MB
09 Regularization/007 L2 regularization in practice.mp4 110MB
29 Python intro_ Functions/008 Classes and object-oriented programming.mp4 108MB
31 Python intro_ Text and plots/004 Making the graphs look nicer.mp4 108MB
13 Measuring model performance/004 APRF example 1_ wine quality.mp4 107MB
12 More on data/006 Data noise augmentation (with devset+test).mp4 106MB
05 Math, numpy, PyTorch/010 Entropy and cross-entropy.mp4 106MB
15 Weight inits and investigations/004 CodeChallenge_ Weight variance inits.mp4 104MB
11 FFNs/002 The MNIST dataset.mp4 101MB
18 Convolution and transformations/005 The Conv2 class in PyTorch.mp4 100MB
30 Python intro_ Flow control/010 Function error checking and handling.mp4 100MB
10 Metaparameters (activations, optimizers)/016 More practice with multioutput ANNs.mp4 100MB
14 FFN milestone projects/002 Project 1_ My solution.mp4 100MB
09 Regularization/008 L1 regularization in practice.mp4 99MB
13 Measuring model performance/005 APRF example 2_ MNIST.mp4 99MB
08 Overfitting and cross-validation/004 Cross-validation -- manual separation.mp4 98MB
10 Metaparameters (activations, optimizers)/017 Optimizers (minibatch, momentum).mp4 98MB
18 Convolution and transformations/001 Convolution_ concepts.mp4 98MB
10 Metaparameters (activations, optimizers)/009 Activation functions.mp4 97MB
10 Metaparameters (activations, optimizers)/023 Learning rate decay.mp4 97MB
21 Transfer learning/001 Transfer learning_ What, why, and when_.mp4 97MB
11 FFNs/005 CodeChallenge_ Data normalization.mp4 96MB
05 Math, numpy, PyTorch/008 Softmax.mp4 96MB
06 Gradient descent/005 Gradient descent in 2D.mp4 96MB
09 Regularization/012 CodeChallenge_ Effects of mini-batch size.mp4 95MB
11 FFNs/007 CodeChallenge_ MNIST and breadth vs. depth.mp4 95MB
07 ANNs/014 CodeChallenge_ more qwerties!.mp4 95MB
31 Python intro_ Text and plots/001 Printing and string interpolation.mp4 95MB
19 Understand and design CNNs/007 CodeChallenge_ How wide the FC_.mp4 94MB
31 Python intro_ Text and plots/006 Images.mp4 94MB
15 Weight inits and investigations/008 Freezing weights during learning.mp4 93MB
18 Convolution and transformations/007 Transpose convolution.mp4 93MB
19 Understand and design CNNs/015 CodeChallenge_ Varying number of channels.mp4 92MB
10 Metaparameters (activations, optimizers)/010 Activation functions in PyTorch.mp4 91MB
30 Python intro_ Flow control/002 If-else statements, part 2.mp4 91MB
30 Python intro_ Flow control/008 while loops.mp4 91MB
30 Python intro_ Flow control/006 Initializing variables.mp4 91MB
21 Transfer learning/002 Transfer learning_ MNIST -_ FMNIST.mp4 90MB
10 Metaparameters (activations, optimizers)/014 Loss functions.mp4 90MB
23 Generative adversarial networks/001 GAN_ What, why, and how.mp4 90MB
07 ANNs/017 Defining models using sequential vs. class.mp4 89MB
19 Understand and design CNNs/009 CodeChallenge_ AEs and occluded Gaussians.mp4 89MB
09 Regularization/010 Batch training in action.mp4 89MB
18 Convolution and transformations/008 Max_mean pooling.mp4 89MB
17 Running models on a GPU/001 What is a GPU and why use it_.mp4 89MB
29 Python intro_ Functions/005 Creating functions.mp4 88MB
05 Math, numpy, PyTorch/011 Min_max and argmin_argmax.mp4 88MB
08 Overfitting and cross-validation/002 Cross-validation.mp4 88MB
15 Weight inits and investigations/007 CodeChallenge_ Identically random weights.mp4 88MB
30 Python intro_ Flow control/003 For loops.mp4 87MB
10 Metaparameters (activations, optimizers)/020 Optimizers comparison.mp4 87MB
31 Python intro_ Text and plots/003 Subplot geometry.mp4 87MB
05 Math, numpy, PyTorch/007 Matrix multiplication.mp4 86MB
05 Math, numpy, PyTorch/013 Random sampling and sampling variability.mp4 85MB
09 Regularization/006 Weight regularization (L1_L2)_ math.mp4 85MB
07 ANNs/001 The perceptron and ANN architecture.mp4 84MB
19 Understand and design CNNs/013 Dropout in CNNs.mp4 83MB
13 Measuring model performance/007 Computation time.mp4 82MB
05 Math, numpy, PyTorch/015 The t-test.mp4 81MB
29 Python intro_ Functions/003 Python libraries (pandas).mp4 81MB
18 Convolution and transformations/009 Pooling in PyTorch.mp4 81MB
05 Math, numpy, PyTorch/012 Mean and variance.mp4 81MB
05 Math, numpy, PyTorch/016 Derivatives_ intuition and polynomials.mp4 80MB
09 Regularization/001 Regularization_ Concept and methods.mp4 80MB
15 Weight inits and investigations/003 Theory_ Why and how to initialize weights.mp4 79MB
08 Overfitting and cross-validation/007 Splitting data into train, devset, test.mp4 79MB
27 Python intro_ Data types/003 Math and printing.mp4 78MB
11 FFNs/010 Shifted MNIST.mp4 78MB
27 Python intro_ Data types/002 Variables.mp4 78MB
06 Gradient descent/004 CodeChallenge_ unfortunate starting value.mp4 77MB
27 Python intro_ Data types/007 Booleans.mp4 77MB
10 Metaparameters (activations, optimizers)/006 Batch normalization.mp4 77MB
10 Metaparameters (activations, optimizers)/019 Optimizers (RMSprop, Adam).mp4 77MB
17 Running models on a GPU/002 Implementation.mp4 77MB
20 CNN milestone projects/005 Project 4_ Psychometric functions in CNNs.mp4 76MB
14 FFN milestone projects/006 Project 3_ My solution.mp4 75MB
24 Ethics of deep learning/004 Will deep learning take our jobs_.mp4 75MB
30 Python intro_ Flow control/007 Single-line loops (list comprehension).mp4 75MB
03 Concepts in deep learning/004 Running experiments to understand DL.mp4 75MB
11 FFNs/011 CodeChallenge_ The mystery of the missing 7.mp4 74MB
10 Metaparameters (activations, optimizers)/011 Activation functions comparison.mp4 74MB
08 Overfitting and cross-validation/001 What is overfitting and is it as bad as they say_.mp4 73MB
03 Concepts in deep learning/002 How models _learn_.mp4 73MB
13 Measuring model performance/002 Accuracy, precision, recall, F1.mp4 73MB
07 ANNs/015 Comparing the number of hidden units.mp4 71MB
30 Python intro_ Flow control/009 Broadcasting in numpy.mp4 71MB
07 ANNs/002 A geometric view of ANNs.mp4 71MB
18 Convolution and transformations/002 Feature maps and convolution kernels.mp4 70MB
24 Ethics of deep learning/005 Accountability and making ethical AI.mp4 70MB
05 Math, numpy, PyTorch/014 Reproducible randomness via seeding.mp4 70MB
15 Weight inits and investigations/001 Explanation of weight matrix sizes.mp4 69MB
06 Gradient descent/001 Overview of gradient descent.mp4 68MB
22 Style transfer/003 The style transfer algorithm.mp4 67MB
06 Gradient descent/002 What about local minima_.mp4 67MB
18 Convolution and transformations/004 Convolution parameters (stride, padding).mp4 67MB
30 Python intro_ Flow control/001 If-else statements.mp4 67MB
22 Style transfer/002 The Gram matrix (feature activation covariance).mp4 66MB
24 Ethics of deep learning/003 Some other possible ethical scenarios.mp4 66MB
29 Python intro_ Functions/006 Global and local variable scopes.mp4 66MB
24 Ethics of deep learning/001 Will AI save us or destroy us_.mp4 66MB
03 Concepts in deep learning/001 What is an artificial neural network_.mp4 65MB
10 Metaparameters (activations, optimizers)/005 The importance of data normalization.mp4 65MB
10 Metaparameters (activations, optimizers)/012 CodeChallenge_ Compare relu variants.mp4 64MB
29 Python intro_ Functions/002 Python libraries (numpy).mp4 63MB
23 Generative adversarial networks/003 CodeChallenge_ Linear GAN with FMNIST.mp4 63MB
13 Measuring model performance/006 CodeChallenge_ MNIST with unequal groups.mp4 62MB
09 Regularization/009 Training in mini-batches.mp4 62MB
10 Metaparameters (activations, optimizers)/018 SGD with momentum.mp4 62MB
10 Metaparameters (activations, optimizers)/007 Batch normalization in practice.mp4 62MB
10 Metaparameters (activations, optimizers)/024 How to pick the right metaparameters.mp4 62MB
23 Generative adversarial networks/007 CodeChallenge_ CNN GAN with CIFAR.mp4 61MB
08 Overfitting and cross-validation/008 Cross-validation on regression.mp4 60MB
11 FFNs/009 Scrambled MNIST.mp4 60MB
09 Regularization/011 The importance of equal batch sizes.mp4 60MB
10 Metaparameters (activations, optimizers)/004 Data normalization.mp4 60MB
31 Python intro_ Text and plots/005 Seaborn.mp4 60MB
18 Convolution and transformations/006 CodeChallenge_ Choose the parameters.mp4 59MB
30 Python intro_ Flow control/004 Enumerate and zip.mp4 59MB
07 ANNs/021 Reflection_ Are DL models understandable yet_.mp4 59MB
19 Understand and design CNNs/003 CNN on shifted MNIST.mp4 58MB
07 ANNs/003 ANN math part 1 (forward prop).mp4 58MB
19 Understand and design CNNs/001 The canonical CNN architecture.mp4 56MB
12 More on data/009 Save and load trained models.mp4 56MB
05 Math, numpy, PyTorch/018 Derivatives_ product and chain rules.mp4 56MB
18 Convolution and transformations/010 To pool or to stride_.mp4 56MB
19 Understand and design CNNs/014 CodeChallenge_ How low can you go_.mp4 55MB
27 Python intro_ Data types/004 Lists (1 of 2).mp4 55MB
01 Introduction/001 How to learn from this course.mp4 55MB
23 Generative adversarial networks/006 CNN GAN with FMNIST.mp4 55MB
01 Introduction/002 Using Udemy like a pro.mp4 54MB
12 More on data/004 What to do about unbalanced designs_.mp4 54MB
09 Regularization/005 Dropout example 2.mp4 54MB
31 Python intro_ Text and plots/002 Plotting dots and lines.mp4 54MB
22 Style transfer/005 CodeChallenge_ Style transfer with AlexNet.mp4 53MB
23 Generative adversarial networks/005 CodeChallenge_ Gaussians with fewer layers.mp4 53MB
10 Metaparameters (activations, optimizers)/022 CodeChallenge_ Adam with L2 regularization.mp4 53MB
17 Running models on a GPU/003 CodeChallenge_ Run an experiment on the GPU.mp4 53MB
24 Ethics of deep learning/002 Example case studies.mp4 53MB
07 ANNs/005 ANN math part 3 (backprop).mp4 53MB
13 Measuring model performance/003 APRF in code.mp4 52MB
07 ANNs/019 CodeChallenge_ convert sequential to class.mp4 51MB
28 Python intro_ Indexing, slicing/001 Indexing.mp4 51MB
05 Math, numpy, PyTorch/002 Spectral theories in mathematics.mp4 51MB
27 Python intro_ Data types/008 Dictionaries.mp4 51MB
14 FFN milestone projects/003 Project 2_ Predicting heart disease.mp4 51MB
07 ANNs/011 Linear solutions to linear problems.mp4 50MB
05 Math, numpy, PyTorch/006 OMG it's the dot product!.mp4 50MB
10 Metaparameters (activations, optimizers)/021 CodeChallenge_ Optimizers and... something.mp4 50MB
11 FFNs/012 Universal approximation theorem.mp4 49MB
16 Autoencoders/001 What are autoencoders and what do they do_.mp4 49MB
29 Python intro_ Functions/004 Getting help on functions.mp4 49MB
14 FFN milestone projects/001 Project 1_ A gratuitously complex adding machine.mp4 49MB
07 ANNs/004 ANN math part 2 (errors, loss, cost).mp4 48MB
28 Python intro_ Indexing, slicing/002 Slicing.mp4 48MB
20 CNN milestone projects/001 Project 1_ Import and classify CIFAR10.mp4 48MB
27 Python intro_ Data types/005 Lists (2 of 2).mp4 47MB
11 FFNs/008 CodeChallenge_ Optimizers and MNIST.mp4 46MB
02 Download all course materials/001 Downloading and using the code.mp4 46MB
05 Math, numpy, PyTorch/017 Derivatives find minima.mp4 45MB
14 FFN milestone projects/005 Project 3_ FFN for missing data interpolation.mp4 45MB
13 Measuring model performance/008 Better performance in test than train_.mp4 45MB
05 Math, numpy, PyTorch/009 Logarithms.mp4 44MB
12 More on data/008 Getting data into colab.mp4 44MB
31 Python intro_ Text and plots/007 Export plots in low and high resolution.mp4 44MB
25 Where to go from here_/001 How to learn topic _X_ in deep learning_.mp4 42MB
12 More on data/011 Where to find online datasets.mp4 42MB
10 Metaparameters (activations, optimizers)/008 CodeChallenge_ Batch-normalize the qwerties.mp4 41MB
21 Transfer learning/004 Famous CNN architectures.mp4 41MB
11 FFNs/004 CodeChallenge_ Binarized MNIST images.mp4 41MB
22 Style transfer/001 What is style transfer and how does it work_.mp4 41MB
13 Measuring model performance/001 Two perspectives of the world.mp4 40MB
06 Gradient descent/006 CodeChallenge_ 2D gradient ascent.mp4 39MB
09 Regularization/002 train() and eval() modes.mp4 38MB
05 Math, numpy, PyTorch/003 Terms and datatypes in math and computers.mp4 38MB
05 Math, numpy, PyTorch/005 Vector and matrix transpose.mp4 38MB
27 Python intro_ Data types/006 Tuples.mp4 36MB
20 CNN milestone projects/003 Project 2_ CIFAR-autoencoder.mp4 33MB
05 Math, numpy, PyTorch/004 Converting reality to numbers.mp4 33MB
30 Python intro_ Flow control/005 Continue.mp4 33MB
10 Metaparameters (activations, optimizers)/001 What are _metaparameters__.mp4 33MB
08 Overfitting and cross-validation/003 Generalization.mp4 32MB
06 Gradient descent/009 Vanishing and exploding gradients.mp4 30MB
29 Python intro_ Functions/001 Inputs and outputs.mp4 29MB
15 Weight inits and investigations/010 Use default inits or apply your own_.mp4 28MB
07 ANNs/012 Why multilayer linear models don't exist.mp4 26MB
20 CNN milestone projects/004 Project 3_ FMNIST.mp4 26MB
11 FFNs/001 What are fully-connected and feedforward networks_.mp4 26MB
29 Python intro_ Functions/007 Copies and referents of variables.mp4 24MB
04 About the Python tutorial/001 Should you watch the Python tutorial_.mp4 24MB
06 Gradient descent/010 Tangent_ Notebook revision history.mp4 22MB
27 Python intro_ Data types/001 How to learn from the Python tutorial.mp4 22MB
19 Understand and design CNNs/016 So many possibilities! How to create a CNN_.mp4 21MB
21 Transfer learning/006 CodeChallenge_ VGG-16.mp4 20MB
05 Math, numpy, PyTorch/001 Introduction to this section.mp4 11MB
02 Download all course materials/002 My policy on code-sharing.mp4 10MB
02 Download all course materials/003 DUDL_PythonCode.zip 701KB
19 Understand and design CNNs/005 Examine feature map activations.en.srt 41KB
19 Understand and design CNNs/002 CNN to classify MNIST digits.en.srt 38KB
07 ANNs/013 Multi-output ANN (iris dataset).en.srt 37KB
07 ANNs/009 Learning rates comparison.en.srt 36KB
19 Understand and design CNNs/012 The EMNIST dataset (letter recognition).en.srt 36KB
07 ANNs/006 ANN for regression.en.srt 36KB
16 Autoencoders/006 Autoencoder with tied weights.en.srt 35KB
19 Understand and design CNNs/004 Classify Gaussian blurs.en.srt 34KB
07 ANNs/008 ANN for classifying qwerties.en.srt 34KB
09 Regularization/004 Dropout regularization in practice.en.srt 33KB
11 FFNs/003 FFN to classify digits.en.srt 33KB
15 Weight inits and investigations/009 Learning-related changes in weights.en.srt 33KB
18 Convolution and transformations/001 Convolution_ concepts.en.srt 33KB
22 Style transfer/004 Transferring the screaming bathtub.en.srt 32KB
23 Generative adversarial networks/002 Linear GAN with MNIST.en.srt 32KB
16 Autoencoders/005 The latent code of MNIST.en.srt 32KB
09 Regularization/003 Dropout regularization.en.srt 31KB
07 ANNs/018 Model depth vs. breadth.en.srt 31KB
29 Python intro_ Functions/005 Creating functions.en.srt 31KB
18 Convolution and transformations/003 Convolution in code.en.srt 31KB
08 Overfitting and cross-validation/005 Cross-validation -- scikitlearn.en.srt 30KB
19 Understand and design CNNs/010 CodeChallenge_ Custom loss functions.en.srt 30KB
07 ANNs/010 Multilayer ANN.en.srt 29KB
12 More on data/003 CodeChallenge_ unbalanced data.en.srt 29KB
16 Autoencoders/003 CodeChallenge_ How many units_.en.srt 29KB
21 Transfer learning/007 Pretraining with autoencoders.en.srt 29KB
08 Overfitting and cross-validation/006 Cross-validation -- DataLoader.en.srt 29KB
12 More on data/007 Data feature augmentation.en.srt 28KB
07 ANNs/007 CodeChallenge_ manipulate regression slopes.en.srt 28KB
30 Python intro_ Flow control/008 while loops.en.srt 28KB
14 FFN milestone projects/004 Project 2_ My solution.en.srt 28KB
27 Python intro_ Data types/007 Booleans.en.srt 28KB
05 Math, numpy, PyTorch/008 Softmax.en.srt 28KB
27 Python intro_ Data types/002 Variables.en.srt 27KB
06 Gradient descent/007 Parametric experiments on g.d.en.srt 27KB
09 Regularization/006 Weight regularization (L1_L2)_ math.en.srt 27KB
31 Python intro_ Text and plots/004 Making the graphs look nicer.en.srt 27KB
10 Metaparameters (activations, optimizers)/015 Loss functions in PyTorch.en.srt 27KB
07 ANNs/001 The perceptron and ANN architecture.en.srt 27KB
27 Python intro_ Data types/003 Math and printing.en.srt 27KB
18 Convolution and transformations/008 Max_mean pooling.en.srt 27KB
29 Python intro_ Functions/008 Classes and object-oriented programming.en.srt 27KB
18 Convolution and transformations/012 Creating and using custom DataLoaders.en.srt 26KB
10 Metaparameters (activations, optimizers)/009 Activation functions.en.srt 26KB
12 More on data/001 Anatomy of a torch dataset and dataloader.en.srt 26KB
21 Transfer learning/008 CIFAR10 with autoencoder-pretrained model.en.srt 26KB
31 Python intro_ Text and plots/006 Images.en.srt 26KB
07 ANNs/016 Depth vs. breadth_ number of parameters.en.srt 26KB
10 Metaparameters (activations, optimizers)/002 The _wine quality_ dataset.en.srt 26KB
30 Python intro_ Flow control/006 Initializing variables.en.srt 26KB
25 Where to go from here_/002 How to read academic DL papers.en.srt 25KB
16 Autoencoders/004 AEs for occlusion.en.srt 25KB
30 Python intro_ Flow control/010 Function error checking and handling.en.srt 25KB
30 Python intro_ Flow control/003 For loops.en.srt 25KB
19 Understand and design CNNs/006 CodeChallenge_ Softcode internal parameters.en.srt 25KB
10 Metaparameters (activations, optimizers)/013 CodeChallenge_ Predict sugar.en.srt 25KB
08 Overfitting and cross-validation/002 Cross-validation.en.srt 25KB
21 Transfer learning/001 Transfer learning_ What, why, and when_.en.srt 25KB
06 Gradient descent/003 Gradient descent in 1D.en.srt 25KB
15 Weight inits and investigations/006 CodeChallenge_ Xavier vs. Kaiming.en.srt 25KB
21 Transfer learning/005 Transfer learning with ResNet-18.en.srt 25KB
11 FFNs/005 CodeChallenge_ Data normalization.en.srt 24KB
05 Math, numpy, PyTorch/016 Derivatives_ intuition and polynomials.en.srt 24KB
19 Understand and design CNNs/008 Do autoencoders clean Gaussians_.en.srt 24KB
31 Python intro_ Text and plots/001 Printing and string interpolation.en.srt 24KB
10 Metaparameters (activations, optimizers)/014 Loss functions.en.srt 24KB
03 Concepts in deep learning/005 Are artificial _neurons_ like biological neurons_.en.srt 24KB
12 More on data/005 Data oversampling in MNIST.en.srt 24KB
18 Convolution and transformations/011 Image transforms.en.srt 24KB
15 Weight inits and investigations/002 A surprising demo of weight initializations.en.srt 24KB
23 Generative adversarial networks/001 GAN_ What, why, and how.en.srt 24KB
12 More on data/002 Data size and network size.en.srt 23KB
03 Concepts in deep learning/003 The role of DL in science and knowledge.en.srt 23KB
19 Understand and design CNNs/011 Discover the Gaussian parameters.en.srt 23KB
31 Python intro_ Text and plots/003 Subplot geometry.en.srt 23KB
06 Gradient descent/008 CodeChallenge_ fixed vs. dynamic learning rate.en.srt 23KB
10 Metaparameters (activations, optimizers)/003 CodeChallenge_ Minibatch size in the wine dataset.en.srt 23KB
30 Python intro_ Flow control/002 If-else statements, part 2.en.srt 23KB
16 Autoencoders/002 Denoising MNIST.en.srt 23KB
15 Weight inits and investigations/005 Xavier and Kaiming initializations.en.srt 23KB
05 Math, numpy, PyTorch/012 Mean and variance.en.srt 22KB
17 Running models on a GPU/001 What is a GPU and why use it_.en.srt 22KB
23 Generative adversarial networks/004 CNN GAN with Gaussians.en.srt 22KB
10 Metaparameters (activations, optimizers)/019 Optimizers (RMSprop, Adam).en.srt 22KB
11 FFNs/006 Distributions of weights pre- and post-learning.en.srt 22KB
12 More on data/010 Save the best-performing model.en.srt 22KB
30 Python intro_ Flow control/007 Single-line loops (list comprehension).en.srt 22KB
30 Python intro_ Flow control/001 If-else statements.en.srt 22KB
06 Gradient descent/005 Gradient descent in 2D.en.srt 21KB
30 Python intro_ Flow control/009 Broadcasting in numpy.en.srt 21KB
03 Concepts in deep learning/001 What is an artificial neural network_.en.srt 21KB
06 Gradient descent/001 Overview of gradient descent.en.srt 21KB
05 Math, numpy, PyTorch/007 Matrix multiplication.en.srt 21KB
21 Transfer learning/003 CodeChallenge_ letters to numbers.en.srt 21KB
27 Python intro_ Data types/004 Lists (1 of 2).en.srt 20KB
10 Metaparameters (activations, optimizers)/016 More practice with multioutput ANNs.en.srt 20KB
29 Python intro_ Functions/003 Python libraries (pandas).en.srt 20KB
29 Python intro_ Functions/002 Python libraries (numpy).en.srt 20KB
18 Convolution and transformations/007 Transpose convolution.en.srt 20KB
10 Metaparameters (activations, optimizers)/004 Data normalization.en.srt 20KB
29 Python intro_ Functions/006 Global and local variable scopes.en.srt 20KB
18 Convolution and transformations/009 Pooling in PyTorch.en.srt 20KB
19 Understand and design CNNs/015 CodeChallenge_ Varying number of channels.en.srt 20KB
05 Math, numpy, PyTorch/015 The t-test.en.srt 19KB
07 ANNs/002 A geometric view of ANNs.en.srt 19KB
13 Measuring model performance/004 APRF example 1_ wine quality.en.srt 19KB
15 Weight inits and investigations/008 Freezing weights during learning.en.srt 19KB
03 Concepts in deep learning/004 Running experiments to understand DL.en.srt 19KB
07 ANNs/017 Defining models using sequential vs. class.en.srt 19KB
09 Regularization/001 Regularization_ Concept and methods.en.srt 19KB
09 Regularization/007 L2 regularization in practice.en.srt 19KB
18 Convolution and transformations/005 The Conv2 class in PyTorch.en.srt 19KB
03 Concepts in deep learning/002 How models _learn_.en.srt 19KB
11 FFNs/002 The MNIST dataset.en.srt 19KB
10 Metaparameters (activations, optimizers)/006 Batch normalization.en.srt 19KB
12 More on data/006 Data noise augmentation (with devset+test).en.srt 19KB
08 Overfitting and cross-validation/004 Cross-validation -- manual separation.en.srt 19KB
15 Weight inits and investigations/004 CodeChallenge_ Weight variance inits.en.srt 18KB
08 Overfitting and cross-validation/001 What is overfitting and is it as bad as they say_.en.srt 18KB
15 Weight inits and investigations/003 Theory_ Why and how to initialize weights.en.srt 18KB
05 Math, numpy, PyTorch/011 Min_max and argmin_argmax.en.srt 18KB
28 Python intro_ Indexing, slicing/001 Indexing.en.srt 18KB
09 Regularization/012 CodeChallenge_ Effects of mini-batch size.en.srt 18KB
18 Convolution and transformations/004 Convolution parameters (stride, padding).en.srt 18KB
13 Measuring model performance/002 Accuracy, precision, recall, F1.en.srt 18KB
28 Python intro_ Indexing, slicing/002 Slicing.en.srt 18KB
15 Weight inits and investigations/007 CodeChallenge_ Identically random weights.en.srt 18KB
10 Metaparameters (activations, optimizers)/023 Learning rate decay.en.srt 18KB
07 ANNs/014 CodeChallenge_ more qwerties!.en.srt 18KB
11 FFNs/007 CodeChallenge_ MNIST and breadth vs. depth.en.srt 18KB
31 Python intro_ Text and plots/002 Plotting dots and lines.en.srt 18KB
09 Regularization/008 L1 regularization in practice.en.srt 17KB
07 ANNs/003 ANN math part 1 (forward prop).en.srt 17KB
15 Weight inits and investigations/001 Explanation of weight matrix sizes.en.srt 17KB
06 Gradient descent/002 What about local minima_.en.srt 17KB
13 Measuring model performance/005 APRF example 2_ MNIST.en.srt 17KB
20 CNN milestone projects/002 Project 1_ My solution.en.srt 17KB
27 Python intro_ Data types/008 Dictionaries.en.srt 17KB
14 FFN milestone projects/002 Project 1_ My solution.en.srt 17KB
10 Metaparameters (activations, optimizers)/010 Activation functions in PyTorch.en.srt 17KB
16 Autoencoders/001 What are autoencoders and what do they do_.en.srt 17KB
20 CNN milestone projects/005 Project 4_ Psychometric functions in CNNs.en.srt 17KB
09 Regularization/009 Training in mini-batches.en.srt 17KB
22 Style transfer/002 The Gram matrix (feature activation covariance).en.srt 17KB
24 Ethics of deep learning/005 Accountability and making ethical AI.en.srt 17KB
10 Metaparameters (activations, optimizers)/024 How to pick the right metaparameters.en.srt 17KB
19 Understand and design CNNs/007 CodeChallenge_ How wide the FC_.en.srt 16KB
11 FFNs/010 Shifted MNIST.en.srt 16KB
05 Math, numpy, PyTorch/013 Random sampling and sampling variability.en.srt 16KB
30 Python intro_ Flow control/004 Enumerate and zip.en.srt 16KB
06 Gradient descent/004 CodeChallenge_ unfortunate starting value.en.srt 16KB
11 FFNs/011 CodeChallenge_ The mystery of the missing 7.en.srt 16KB
31 Python intro_ Text and plots/005 Seaborn.en.srt 16KB
19 Understand and design CNNs/001 The canonical CNN architecture.en.srt 16KB
09 Regularization/010 Batch training in action.en.srt 16KB
07 ANNs/005 ANN math part 3 (backprop).en.srt 15KB
24 Ethics of deep learning/003 Some other possible ethical scenarios.en.srt 15KB
22 Style transfer/003 The style transfer algorithm.en.srt 15KB
24 Ethics of deep learning/004 Will deep learning take our jobs_.en.srt 15KB
17 Running models on a GPU/002 Implementation.en.srt 15KB
10 Metaparameters (activations, optimizers)/020 Optimizers comparison.en.srt 15KB
07 ANNs/015 Comparing the number of hidden units.en.srt 15KB
21 Transfer learning/002 Transfer learning_ MNIST -_ FMNIST.en.srt 15KB
27 Python intro_ Data types/005 Lists (2 of 2).en.srt 15KB
14 FFN milestone projects/005 Project 3_ FFN for missing data interpolation.en.srt 14KB
24 Ethics of deep learning/001 Will AI save us or destroy us_.en.srt 14KB
18 Convolution and transformations/010 To pool or to stride_.en.srt 14KB
13 Measuring model performance/007 Computation time.en.srt 14KB
19 Understand and design CNNs/013 Dropout in CNNs.en.srt 14KB
19 Understand and design CNNs/009 CodeChallenge_ AEs and occluded Gaussians.en.srt 14KB
18 Convolution and transformations/002 Feature maps and convolution kernels.en.srt 14KB
05 Math, numpy, PyTorch/006 OMG it's the dot product!.en.srt 14KB
07 ANNs/004 ANN math part 2 (errors, loss, cost).en.srt 14KB
23 Generative adversarial networks/003 CodeChallenge_ Linear GAN with FMNIST.en.srt 14KB
08 Overfitting and cross-validation/007 Splitting data into train, devset, test.en.srt 14KB
10 Metaparameters (activations, optimizers)/005 The importance of data normalization.en.srt 14KB
10 Metaparameters (activations, optimizers)/011 Activation functions comparison.en.srt 14KB
05 Math, numpy, PyTorch/002 Spectral theories in mathematics.en.srt 14KB
05 Math, numpy, PyTorch/018 Derivatives_ product and chain rules.en.srt 14KB
13 Measuring model performance/006 CodeChallenge_ MNIST with unequal groups.en.srt 13KB
07 ANNs/021 Reflection_ Are DL models understandable yet_.en.srt 12KB
01 Introduction/002 Using Udemy like a pro.en.srt 12KB
25 Where to go from here_/001 How to learn topic _X_ in deep learning_.en.srt 12KB
05 Math, numpy, PyTorch/017 Derivatives find minima.en.srt 12KB
07 ANNs/011 Linear solutions to linear problems.en.srt 12KB
19 Understand and design CNNs/003 CNN on shifted MNIST.en.srt 12KB
27 Python intro_ Data types/006 Tuples.en.srt 12KB
08 Overfitting and cross-validation/008 Cross-validation on regression.en.srt 12KB
13 Measuring model performance/008 Better performance in test than train_.en.srt 12KB
14 FFN milestone projects/006 Project 3_ My solution.en.srt 12KB
05 Math, numpy, PyTorch/014 Reproducible randomness via seeding.en.srt 12KB
11 FFNs/012 Universal approximation theorem.en.srt 12KB
23 Generative adversarial networks/007 CodeChallenge_ CNN GAN with CIFAR.en.srt 12KB
10 Metaparameters (activations, optimizers)/018 SGD with momentum.en.srt 12KB
05 Math, numpy, PyTorch/009 Logarithms.en.srt 11KB
31 Python intro_ Text and plots/007 Export plots in low and high resolution.en.srt 11KB
10 Metaparameters (activations, optimizers)/012 CodeChallenge_ Compare relu variants.en.srt 11KB
11 FFNs/009 Scrambled MNIST.en.srt 11KB
29 Python intro_ Functions/004 Getting help on functions.en.srt 11KB
10 Metaparameters (activations, optimizers)/007 Batch normalization in practice.en.srt 11KB
14 FFN milestone projects/003 Project 2_ Predicting heart disease.en.srt 11KB
14 FFN milestone projects/001 Project 1_ A gratuitously complex adding machine.en.srt 11KB
05 Math, numpy, PyTorch/003 Terms and datatypes in math and computers.en.srt 11KB
29 Python intro_ Functions/001 Inputs and outputs.en.srt 11KB
20 CNN milestone projects/001 Project 1_ Import and classify CIFAR10.en.srt 11KB
22 Style transfer/005 CodeChallenge_ Style transfer with AlexNet.en.srt 10KB
13 Measuring model performance/001 Two perspectives of the world.en.srt 10KB
10 Metaparameters (activations, optimizers)/022 CodeChallenge_ Adam with L2 regularization.en.srt 10KB
09 Regularization/002 train() and eval() modes.en.srt 10KB
18 Convolution and transformations/006 CodeChallenge_ Choose the parameters.en.srt 10KB
30 Python intro_ Flow control/005 Continue.en.srt 10KB
05 Math, numpy, PyTorch/005 Vector and matrix transpose.en.srt 10KB
19 Understand and design CNNs/014 CodeChallenge_ How low can you go_.en.srt 10KB
11 FFNs/008 CodeChallenge_ Optimizers and MNIST.en.srt 10KB
17 Running models on a GPU/003 CodeChallenge_ Run an experiment on the GPU.en.srt 10KB
07 ANNs/019 CodeChallenge_ convert sequential to class.en.srt 10KB
05 Math, numpy, PyTorch/004 Converting reality to numbers.en.srt 10KB
09 Regularization/011 The importance of equal batch sizes.en.srt 9KB
02 Download all course materials/001 Downloading and using the code.en.srt 9KB
13 Measuring model performance/003 APRF in code.en.srt 9KB
10 Metaparameters (activations, optimizers)/021 CodeChallenge_ Optimizers and... something.en.srt 9KB
23 Generative adversarial networks/006 CNN GAN with FMNIST.en.srt 9KB
07 ANNs/012 Why multilayer linear models don't exist.en.srt 9KB
09 Regularization/005 Dropout example 2.en.srt 9KB
24 Ethics of deep learning/002 Example case studies.en.srt 9KB
06 Gradient descent/009 Vanishing and exploding gradients.en.srt 9KB
12 More on data/009 Save and load trained models.en.srt 9KB
23 Generative adversarial networks/005 CodeChallenge_ Gaussians with fewer layers.en.srt 9KB
12 More on data/008 Getting data into colab.en.srt 9KB
08 Overfitting and cross-validation/003 Generalization.en.srt 9KB
21 Transfer learning/004 Famous CNN architectures.en.srt 9KB
12 More on data/011 Where to find online datasets.en.srt 8KB
06 Gradient descent/006 CodeChallenge_ 2D gradient ascent.en.srt 8KB
10 Metaparameters (activations, optimizers)/008 CodeChallenge_ Batch-normalize the qwerties.en.srt 8KB
11 FFNs/004 CodeChallenge_ Binarized MNIST images.en.srt 7KB
10 Metaparameters (activations, optimizers)/001 What are _metaparameters__.en.srt 7KB
29 Python intro_ Functions/007 Copies and referents of variables.en.srt 7KB
20 CNN milestone projects/003 Project 2_ CIFAR-autoencoder.en.srt 7KB
11 FFNs/001 What are fully-connected and feedforward networks_.en.srt 7KB
19 Understand and design CNNs/016 So many possibilities! How to create a CNN_.en.srt 7KB
22 Style transfer/001 What is style transfer and how does it work_.en.srt 6KB
15 Weight inits and investigations/010 Use default inits or apply your own_.en.srt 6KB
04 About the Python tutorial/001 Should you watch the Python tutorial_.en.srt 6KB
20 CNN milestone projects/004 Project 3_ FMNIST.en.srt 5KB
21 Transfer learning/006 CodeChallenge_ VGG-16.en.srt 5KB
27 Python intro_ Data types/001 How to learn from the Python tutorial.en.srt 5KB
26 Bonus section/001 Bonus content.html 4KB
05 Math, numpy, PyTorch/001 Introduction to this section.en.srt 3KB
06 Gradient descent/010 Tangent_ Notebook revision history.en.srt 3KB
02 Download all course materials/002 My policy on code-sharing.en.srt 3KB
07 ANNs/020 Diversity of ANN visual representations.html 1KB
0. Websites you may like/[FCS Forum].url 133B
0. Websites you may like/[FreeCourseSite.com].url 127B
0. Websites you may like/[CourseClub.ME].url 122B
0. Websites you may like/[GigaCourse.Com].url 49B