Machine learning is one of the fastest-growing and most exciting fields out there, and deep learning represents its true bleeding edge. In this course, you will develop a clear understanding of the motivation for deep learning, and design intelligent systems that learn from complex and/or large-scale datasets. We’ll show you how to train and optimize basic neural networks, convolutional neural networks, and long short term memory networks.
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 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: Google
Course Curriculum
From Machine Learning to Deep Learning | |||
What is Deep Learning? | 00:01:00 | ||
Course Overview | 00:02:00 | ||
Solving Problems – Big and Small | 00:02:00 | ||
Let’s Get Started! | 00:01:00 | ||
Supervised Classification | 00:01:00 | ||
Quiz: Classification For Detection | 00:01:00 | ||
Quiz: Classification For Ranking | 00:01:00 | ||
Let’s make a deal | 00:01:00 | ||
Training Your Logistic Classifier | 00:02:00 | ||
Quiz: Softmax | 00:01:00 | ||
Quiz: Softmax Quiz Part 2 | 00:01:00 | ||
Quiz: Softmax Quiz Part 3 | 00:02:00 | ||
One-Hot Encoding | 00:01:00 | ||
Quiz: One-Hot Encoding Quiz | 00:01:00 | ||
Cross Entropy | 00:02:00 | ||
Minimizing Cross Entropy | 00:02:00 | ||
Practical Aspects of Learning | 00:01:00 | ||
Numerical Stability | 00:01:00 | ||
Normalized Inputs and Initial Weights | 00:03:00 | ||
Lather. Rinse. Repeat. | 00:01:00 | ||
Measuring Performance | 00:04:00 | ||
Transition: Overfitting -> Dataset Size | 00:01:00 | ||
Validation and Test Set Size | 00:02:00 | ||
Quiz: Validation Set Size | 00:01:00 | ||
Validation Test Set Size Continued | 00:01:00 | ||
Optimizing a Logistic Classifier | 00:01:00 | ||
Stochastic Gradient Descent | 00:03:00 | ||
Momentum and Learning Rate Decay | 00:02:00 | ||
Parameter Hyperspace! | 00:02:00 | ||
Assignment: notMNIST | |||
Getting Started with notMNIST | 00:03:00 | ||
Problem 1: Display some images | 00:01:00 | ||
Convert image dataset into 3D array | 00:02:00 | ||
Problem 2: Verify normalized images | 00:01:00 | ||
Problem 3: Verify data is balanced | 00:01:00 | ||
Splitting the dataset into batches | 00:01:00 | ||
Problem 4: Shuffle samples and verify | 00:02:00 | ||
Problem 5: Find overlapping samples | 00:00:00 | ||
Problem 6: Train a simple ML model | 00:02:00 | ||
Deep Neural Networks | |||
Intro to Deep Neural Networks | 00:01:00 | ||
Quiz: Number of Parameters | 00:01:00 | ||
Linear Models are Limited | 00:02:00 | ||
Quiz: Rectified Linear Units | 00:01:00 | ||
Network of ReLUs | 00:01:00 | ||
No Neurons | 00:01:00 | ||
The Chain Rule | 00:01:00 | ||
Backprop Through time | 00:01:00 | ||
Training a Deep Learning Network | 00:02:00 | ||
Regularization Intro | 00:01:00 | ||
Regularization | 00:01:00 | ||
Regularization Quiz | 00:01:00 | ||
Dropout | 00:02:00 | ||
Dropout Pt. 2 | 00:01:00 | ||
Next Assignment: Regularization | 00:01:00 | ||
Convolutional Neural Networks | |||
Intro To CNNs | 00:01:00 | ||
Color | 00:01:00 | ||
Statistical Invariance | 00:02:00 | ||
Convolutional Networks | 00:04:00 | ||
Feature Map Sizes | 00:01:00 | ||
Convolutions continued | 00:01:00 | ||
Explore The Design Space | 00:03:00 | ||
1×1 Convolutions | 00:02:00 | ||
Inception Module | 00:02:00 | ||
Conclusion | 00:01:00 | ||
Next Assignment: ConvNets | 00:01:00 | ||
Deep Models for Text and Sequences | |||
Train a text embedding model | 00:01:00 | ||
Semantic Ambiguity | 00:01:00 | ||
Unsupervised Learning | 00:01:00 | ||
Embeddings | 00:02:00 | ||
Word2Vec | 00:01:00 | ||
tSNE | 00:01:00 | ||
Word2Vec Details | 00:02:00 | ||
Quiz: Word Analogy Game | 00:01:00 | ||
Analogies | 00:01:00 | ||
Sequences of Varying Length | 00:01:00 | ||
RNNs | 00:02:00 | ||
Backprop Through time | 00:01:00 | ||
Vanishing / Exploding Gradients | 00:01:00 | ||
LSTM | 00:01:00 | ||
Memory Cell | 00:01:00 | ||
LSTM Cell | 00:02:00 | ||
LSTM Cell 2 | 00:01:00 | ||
Regularization | 00:01:00 | ||
Beam Search | 00:02:00 | ||
Play Legos | 00:01:00 | ||
Captioning and Translation | 00:02:00 | ||
Course Outro | 00:01:00 | ||
Assessment | |||
Submit Your Assignment | 00:00:00 | ||
Certification | 00:00:00 |
Course Reviews
No Reviews found for this course.