You must be logged in to take this course → LOGIN | REGISTER NOW
This course teaches you the practical aspects of neural networks ranging from topics like hyperparameter tuning to how your optimization algorithm runs in the system.
You will be working on making critical decisions on improving your network by selecting number of layers and hidden units, the learning rate and activation functions in this course. This is a highly intuitive course which enables you to convert your ideas to code and experiments and get result.
Assessment
This course does not involve any written exams. Students need to answer 5 assignment questions to complete the course, the answers will be in the form of written work in pdf or word. Students can write the answers in their own time. Each answer needs to be 200 words (1 Page). Once the answers are submitted, the tutor will check and assess the work.
Certification
Edukite courses are free to study. To successfully complete a course you must submit all the assignment of the course as part of the assessment. Upon successful completion of a course, you can choose to make your achievement formal by obtaining your Certificate at a cost of £49.
Having an Official Edukite Certification is a great way to celebrate and share your success. You can:
- Add the certificate to your CV or resume and brighten up your career
- Show it to prove your success
Course Credit: Deep Learning AI
Course Curriculum
Module 01 | |||
Neural Networks – Train Dev Test sets | 00:12:00 | ||
Neural Networks – Bias Variance | 00:09:00 | ||
Neural Networks – Basic Recipe for Machine Learning | 00:06:00 | ||
Neural Networks – Regularization | 00:10:00 | ||
Neural Networks – Why regularization reduces overfitting | 00:07:00 | ||
Neural Networks – Dropout Regularization | 00:09:00 | ||
Neural Networks – Understanding Dropout | 00:07:00 | ||
Neural Networks – Other regularization methods | 00:08:00 | ||
Neural Networks – Normalizing inputs | 00:06:00 | ||
Neural Networks – Vanishing Exploding gradients | 00:06:00 | ||
Neural Networks – Weight Initialization for Deep Networks | 00:06:00 | ||
Neural Networks – Numerical approximation of gradients | 00:07:00 | ||
Module 02 | |||
Neural Networks – Gradient checking | 00:07:00 | ||
Neural Networks – Gradient Checking Implementation Notes | 00:05:00 | ||
Neural Networks – Yoshua Bengio interview | 00:26:00 | ||
Neural Networks – Mini batch gradient descent | 00:11:00 | ||
Neural Networks – Understanding mini batch gradient descent | 00:11:00 | ||
Neural Networks – Exponentially weighted averages | 00:06:00 | ||
Neural Networks – Understanding exponentially weighted averages | 00:10:00 | ||
Neural Networks – Bias correction in exponentially weighted averages | 00:04:00 | ||
Neural Networks – Gradient descent with momentum | 00:09:00 | ||
Neural Networks – RMSprop | 00:08:00 | ||
Neural Networks – Adam optimization algorithm | 00:07:00 | ||
Neural Networks – Learning rate decay | 00:07:00 | ||
Neural Networks – The problem of local optima | 00:05:00 | ||
Module 03 | |||
Neural Networks – Yuanqing Lin interview | 00:14:00 | ||
Neural Networks – Tuning process | 00:07:00 | ||
Neural Networks – Using an appropriate scale to | 00:09:00 | ||
Neural Networks – Hyperparameters tuning in prac | 00:07:00 | ||
Neural Networks – Normalizing activations in a n | 00:09:00 | ||
Neural Networks – Fitting Batch Norm into a neur | 00:13:00 | ||
Neural Networks – Why does Batch Norm work | 00:12:00 | ||
Neural Networks – Batch Norm at test time | 00:06:00 | ||
Neural Networks – Softmax Regression | 00:12:00 | ||
Neural Networks – Training a softmax classifier | 00:10:00 | ||
Neural Networks – Deep learning frameworks | 00:04:00 | ||
Neural Networks – TensorFlow | 00:16:00 | ||
Assessment | |||
Submit Your Assignment | 00:00:00 | ||
Certification | 00:00:00 |
Course Reviews
No Reviews found for this course.