4.15 (57 reviews)
☑ Basic Machine Learning principals in Python
☑ Using scikit-learn to produce ML algorithms
☑ Create a REST API for any ML Model
☑ Some Python Pandas Fundamentals (saving, searching, etc)
Machine learning is simply a computer learning from data instead of following a recipe. It's meant to mimic how people (and perhaps other animals) learn while still being grounded in mathematics.
This post is meant to get you started with a basic machine learning model.
Now, we're not re-creating Alexa, Siri, Cortana, or Google Assistant but we are going to create a brand new machine learning program from scratch.
This course is meant to be easy assuming you know a bit of Python Programming.
Check out the demo in the course so you can get an exact sense of what you're going to be building. Our Github Repo also has the code for you to play around with.
Let's do this!
Setup Jupyter Locally
The non-machine learning way
Bots the Old Way- Instruction-based Responses
Tag our Conversations
Dataset as Inputs & Outputs
Vectorize our Data
Training & Predictions
Train our Model
Export & Import Model for Reuse
Retraining with New Data
Dataset Saving & Updates
Store Dataset with Pandas
Adding to the Dataset
Rest API & Responses
Creating a Rest API Model Service
Responses from Predictions
Thank you and next steps
This course is a good intro, but skims so fast over the surface. If you run into technical issues getting your environment working you'll want to get acquainted with stackoverflow and Google because this course barrels ahead as if it'll all be smooth sailing.
Good course! Learned and built a supervised learning bot, kinda cool! Only feedback is that you code and talk quickly without time for me to write at the same time leading me to have to frequently pause. Also at the very end got an assertion error and had to relearn so troubleshoot on the fly, but it worked! Thanks for the new concepts!
He doesnt really explain a lot of aspects of machine learning like what is vectorizing and why we use it, why do we use multilabelbinarizer, i dont get the point of the REST API as I feel that it doesnt fit in this course, maybe you could use these 33 minutes to show other classifiers/models and explain better the responses part. Overall I learned many things as a newbie at ML.
A fast introduction. Needs more theory to be able to go beyond what is built. I hope there is a follow on class with more depth!