Master Classes
Deep Learning
Only for Members
The following list is the links to the classrooms of the Deep Learning.
Study guide for Introducation to Deep Learning
The following information provides study guideline to help people study Deep Learning by themselves. These Youtube videos will provide enough information to people so they can get ready to take Andrew Ng's Deep Learning Specialist Program. Sedisbus Education provides limited number of online classes to learn together the topics. For more information about it please contact Sedibus Education.
1. Applications of Deep Learning
(Week 1)
Machine learning : living in the age of ai
Top Deep Learning Projects | Artificial Intelligence Projects | Deep Learning Training | Edureka
Project examples (***)
2. Let's try to hear what a Google employer talks about Deep Learning
(Week 2)
3. Let's learn about the foundation concept of Deep Learning
But what is a Neural Network? | Deep learning, chapter 1 (***)
Neural networks and deep learning - Michael Neilsen book ( explanation about bias)
Gradient descent, how neural networks learn | Deep learning, chapter 2
Derivative as a concept | Derivatives introduction | AP Calculus AB | Khan Academy
Gradients and Partial Derivatives
What is backpropagation really doing? | Deep learning, chapter 3
4. Now let,s go back to the Google employer's talk and see how much more you understood.
(Week 5)
5. Let's set up the system for actual coding
(Week 6)
Installations for Deep Learning : Anaconda, Jupyter Notebook, Tensorflow, Kera
Using Google Colap , Learn Keras
6. Let's build an application
(Week 7)
7. Let's build more advanced one (optional)
How to Classify Photos of Dogs and Cats (with 97% accuracy)
https://machinelearningmastery.com/how-to-develop-a-convolutional-neural-network-to-classify-photos-of-dogs-and-cats/
Image Classifier - Cats🐱 vs Dogs🐶
Leveraging Convolutional Neural Networks (CNNs) and Google Colab’s Free GPU
https://towardsdatascience.com/image-classifier-cats-vs-dogs-with-convolutional-neural-networks-cnns-and-google-colabs-4e9af21ae7a8
A friendly introduction to Convolutional Neural Networks and Image Recognition
https://www.youtube.com/watch?v=2-Ol7ZB0MmU
Statistics for Deep Learning
https://www.youtube.com/watch?v=tcusIOfI_GM
Calculus for Deep Learning
https://www.youtube.com/watch?v=WUvTyaaNkzM&list=PLOuNXk3Eq9Y9_iCLsLJORbuyzQWdKWRoI
Deep Learning ( Andrew Ng)
Tuning Process (C2W3L01)
https://www.youtube.com/watch?v=AXDByU3D1hA
Using an Appropriate Scale (C2W3L02)
https://www.youtube.com/watch?v=cSoK_6Rkbfg
Hyperparameter Tuning in Practice (C2W3L03)
https://www.youtube.com/watch?v=wKkcBPp3F1Y
Normalizing Activations in a Network (C2W3L04)
Normalizing Activations in a Network (C2W3L04)
Why Regularization Reduces Overfitting (C2W1L05)
https://www.youtube.com/watch?v=NyG-7nRpsW8
Dropout Regularization (C2W1L06)
https://www.youtube.com/watch?v=D8PJAL-MZv8&t=53s
Understanding Dropout (C2W1L07)
https://www.youtube.com/watch?v=ARq74QuavAo
Other Regularization Methods (C2W1L08)
https://www.youtube.com/watch?v=BOCLq2gpcGU
Normalizing Inputs (C2W1L09)
https://www.youtube.com/watch?v=FDCfw-YqWTE
Vanishing/Exploding Gradients (C2W1L10)
https://www.youtube.com/watch?v=qhXZsFVxGKo
Weight Initialization in a Deep Network (C2W1L11)
https://www.youtube.com/watch?v=s2coXdufOzE&t=2s
Weight Initialization explained | A way to reduce the vanishing gradient problem
https://www.youtube.com/watch?v=8krd5qKVw-Q
Numerical Approximations of Gradients (C2W1L12)
https://www.youtube.com/watch?v=y1xoI7mBtOc
Gradient Checking (C2W1L13)
https://www.youtube.com/watch?v=QrzApibhohY
Gradient Checking Implementation Notes (C2W1L14)
https://www.youtube.com/watch?v=4Ct3Yujl1dk
Mini Batch Gradient Descent (C2W2L01)
https://www.youtube.com/watch?v=4qJaSmvhxi8
Understanding Mini-Batch Gradient Dexcent (C2W2L02)
https://www.youtube.com/watch?v=-_4Zi8fCZO4
Exponentially Weighted Averages (C2W2L03)
https://www.youtube.com/watch?v=lAq96T8FkTw
Understanding Exponentially Weighted Averages (C2W2L04)
https://www.youtube.com/watch?v=NxTFlzBjS-4
Bias Correction of Exponentially Weighted Averages (C2W2L05)
https://www.youtube.com/watch?v=lWzo8CajF5s
Gradient Descent With Momentum (C2W2L06)
https://www.youtube.com/watch?v=k8fTYJPd3_I
RMSProp (C2W2L07)
https://www.youtube.com/watch?v=_e-LFe_igno
Adam Optimization Algorithm (C2W2L08)
https://www.youtube.com/watch?v=JXQT_vxqwIs
Learning Rate Decay (C2W2L09)
https://www.youtube.com/watch?v=QzulmoOg2JE
Tuning Process (C2W3L01)
https://www.youtube.com/watch?v=AXDByU3D1hA
Using an Appropriate Scale (C2W3L02)
https://www.youtube.com/watch?v=cSoK_6Rkbfg
Hyperparameter Tuning in Practice (C2W3L03)
https://www.youtube.com/watch?v=wKkcBPp3F1Y
Normalizing Activations in a Network (C2W3L04)
https://www.youtube.com/watch?v=tNIpEZLv_eg
Fitting Batch Norm Into Neural Networks (C2W3L05)
https://www.youtube.com/watch?v=em6dfRxYkYU
Why Does Batch Norm Work? (C2W3L06)
https://www.youtube.com/watch?v=nUUqwaxLnWs
Batch Norm At Test Time (C2W3L07)
https://www.youtube.com/watch?v=5qefnAek8OA
Softmax Regression (C2W3L08)
https://www.youtube.com/watch?v=LLux1SW--oM
Training Softmax Classifier (C2W3L09)
https://www.youtube.com/watch?v=ueO_Ph0Pyqk
TensorFlow (C2W3L11)
https://www.youtube.com/watch?v=S9ElPZupUsE
Improving Model Performance (C3W1L01)
https://www.youtube.com/watch?v=dFX8k1kXhOw
Orthogonalization (C3W1L02 )
https://www.youtube.com/watch?v=UEtvV1D6B3s
Single Number Evaluation Metric (C3W1L03)
https://www.youtube.com/watch?v=sofffBNhVSo
Satisficing and Optimizing Metrics (C3W1L04)
https://www.youtube.com/watch?v=BH9mlmdXzzI
Train/Dev/Test Set Distributions (C3W1L05)
https://www.youtube.com/watch?v=M3qpIzy4MQk
Sizeof Dev and Test Sets (C3W1L06)
https://www.youtube.com/watch?v=_Fe5kKmFieg