Coursera
Subscription
CourseraConvolutional Neural Networks
4.8(42,588)571k studentsINTERMEDIATEEnglish
Korshub's take
The computer vision course inside deep learning's most cited specialization
The fourth course in Andrew Ng's Deep Learning Specialization, Convolutional Neural Networks takes you from the fundamentals of computer vision into building CNNs, residual networks, and applying neural style transfer — the techniques behind autonomous driving and facial recognition systems.
Who it's for
An intermediate-level course best suited to learners who already have deep learning fundamentals under their belt. It's a proven, high-demand track with 571,226 learners.
What you'll take away
- Building convolutional neural networks and residual architectures
- Applying transfer learning and fine-tuning to vision tasks
- Practical work with TensorFlow, embeddings, and model training
If you're serious about a computer vision or applied ML career, this is one of the most respected, widely-referenced courses in the field.
About this course
In the fourth course of the Deep Learning Specialization, you will understand how computer vision has evolved and become familiar with its exciting applications such as autonomous driving, face recognition, reading radiology images, and more.
By the end, you will be able to build a convolutional neural network, including recent variations such as residual networks; apply convolutional networks to visual detection and recognition tasks; and use neural style transfer to generate art and apply the
Skills you'll gain: Convolutional Neural Networks, Computer Vision, Image Analysis, Transfer Learning, Deep Learning, Fine-tuning, Artificial Neural Networks, Tensorflow, Applied Machine Learning, Data Preprocessing, Embeddings, Feature Engineering, Model Training, Network Architecture.
Access
Advertisement
