As of today, the channel contains videos for three different courses:
▫️Computer Vision
▫️Natural Language Processing
▫️Tabular Data
I'm starting with Computer Vision.
👇
Day 1 of #MLU goes over the topics that will be covered during the course:
▫️Intro to ML and CV
▫️Training Neural Networks and CNNs
▫️Classic CNN architectures
▫️Project: Image classification
▫️Object detection
▫️Semantic segmentation
▫️Transfer learning and AutoML
👇
By the end of the course, you'll have:
▫️Fundamental understanding of ML
▫️Practical knowledge of Computer Vision
Specifically:
▫️Data preprocessing
▫️Common ML algorithms
▫️How to evaluate a model
▫️Model training
▫️Common CV applications
👇
Something really cool: you'll get some hands-on with Amazon SageMaker, which is @awscloud's environment to build and deploy Machine Learning applications.
I spend a lot of time every day using SageMaker. It's pretty cool! You won't want to miss this.
👇
How much can you get out of 5 minutes every day?
I'll find out and I'll let you know.
But you don't have to wait and you can join me now.
Let's do this!
• • •
Missing some Tweet in this thread? You can try to
force a refresh
In machine learning, data is represented by vectors. Essentially, training a learning algorithm is finding more descriptive representations of data through a series of transformations.
Linear algebra is the study of vector spaces and their transformations.