Machine Learning Basics

Tom Walder (01.Oct.2017 at 09:55, 45 min)
Talk at PHP North West 2017 (English - UK)

Rating: 5 of 5

Machine Learning (ML) isn’t Skynet, but it is a type of Artificial Intelligence.

It’s certainly more easily accessible than ever - and could add great value to your software.

We’ll cover the basic principles of the Machine Learning process: DATA > LEARNING > PREDICTION

There are easily accessible, pre-trained machine learning REST APIs for image, text, video and voice analysis.

These can be a real short-cut to taking advantage of ML quickly in your applications.

We’ll look at some of these APIs and their application in real-world software.

When your problem is harder, more niche or needs some customisation, you’ll need to “train your own model”.

We’ll discuss the importance of data in Machine learning - the starting point for any new model.

There are some great open-source tools (in PHP as well as the popular TensorFlow in Python) for building and training your own models - and with scalable, low-cost cloud servers you can train new models quickly in the cloud.

Who are you?

Claim talk

Talk claims have been moved to the new site.

Please login to the new site to claim your talk

Comments closed.


Rating: 5 of 5

01.Oct.2017 at 10:42 by Simon R Jones (46 comments) via Web2 LIVE

Fascinating overview of Machine Learning - and especially how easy it is to start playing with now. Great talk!

Rating: 5 of 5

01.Oct.2017 at 10:50 by Oliver Rose (6 comments) via Android app

A very interesting primer for machine learning, which gave a good example of what you need to do to successfully train your models

Rating: 5 of 5

01.Oct.2017 at 11:04 by Ian Smith (19 comments) via Web2 LIVE

Great overview of current state of machine learning, a summary of tools Tom used was also very helpful in knowing what to get started with.

Rating: 4 of 5

01.Oct.2017 at 14:59 by Robert Mulvaney (4 comments) via Web2 LIVE

Good talk, really helped get a basic understand of what ML is (and isn't) and where to start looking to learn more.

Would have liked to have seen a bit more code and demos of ML working in practice - even if it'd have to be a case of "here's one I trained earlier..."

Rating: 5 of 5

01.Oct.2017 at 16:08 by Claire Gurman (6 comments) via Web2 LIVE

Brilliant overview of how it works and some readily available tools. I did some about 12 years ago in Perl for in silico drug design and have thought about picking it up again from time to time; this talk has certainly encouraged me to try it again!

Rating: 5 of 5

01.Oct.2017 at 21:56 by Stefan Kecskes (16 comments)

Only ML basics, but solid ones. I really enjoyed PHP-ML. Would like to see how you store the model and reuse it or improve it. Also missed the integration and examples of using tensorflow with PHP. But overall, it was great basics intro to ML. Thanks for that.

Rating: 5 of 5

01.Oct.2017 at 22:22 by John Cleary (36 comments) via Web2 LIVE

It's not often a delegate opens his questions with "your talk is why I bought my ticket - and I'm so glad I did"

Tom's talk was great; pitched at just the right level and had some good examples. If time permitted I would like to have seen a 3 dimensional data set. All in all very enjoyable (and funny too - love those 80's references)

#KillSarahConnor #ML

Rating: 5 of 5

01.Oct.2017 at 23:45 by Paul (3 comments) via Web2 LIVE

Great well structured talk. The example problem was simple to understand and gave context to the earlier explanation of Machine Learning.

Rating: 5 of 5

02.Oct.2017 at 10:01 by Stephan Hochdörfer (206 comments) via Web2 LIVE

Great talk, gave me some good insights what ML really is about and how to get started.

Rating: 4 of 5

03.Oct.2017 at 07:53 by Iain Fogg (21 comments) via Web2 LIVE

Good intro to the topic, which I knew nothing about prior to the session. Left feeling like I understood the basics of the topic with a couple of tools to try out, so could certainly progress this now myself. A stronger example would have been useful, but maybe not possible within the time constraints.

© 2019