TransformX Virtual Conference

120 Speakers + 80 Sessions + 20K Attendees

TransformX Logo

The Foundational Guide

On Training and Building Machine Learning Models


By Scale Team, Barrett Williams and Marwan Mattar on September 15th, 2022

The Foundational Guide
Copy link

Training Models for Machine Learning

What distinguishes a ML model from simple heuristics or hard-coded feature detectors is a series of “weights,” typically floating point numbers, linked by functions. The system is trained through trial and error, attempting to minimize error (known as “loss” in the ML world) over time. There are too many of these weights to adjust them manually or selectively; they must be “trained” iteratively, in an automated fashion to be useful.

Chapters

    Copy link

    What Are ML Models


    Copy link

    What types of data can ML models be trained on?


    Copy link

    What are some common classes or types of ML models?


    Copy link

    What are some common layer types in deep neural networks?


    Copy link

    Choosing Model Metrics


    Copy link

    Model Training


    Copy link

    Best Practices for Developing Computer Vision Applications


    Copy link

    Best Practices for Developing Natural Language Applications


    Copy link

    Conclusion

    Training ML models shouldn’t be a daunting proposition given the smorgasbord of tools available today. It’s never been easier to get started.

    That said, don’t let ML be a solution looking for a problem. Prove that simpler approaches aren’t more effective before you land on a CNN, DNN, or LSTM as the ideal solution.

    Training models can feel like an art, but really it’s best to approach it as a science. Hyperparameters and quirks in your dataset may dictate outcomes, but dig in deeper: eventually you can prove or disprove hypotheses as to what’s causing better or worse outcomes.

    It’s important to be systematic and methodical: it’s best to keep an engineer’s log or notebook. Tracking hyperparameters in GitHub is largely insufficient; you should ruthlessly test your models for regressions, track aggregate and specific performance metrics, and use tooling where possible to take the tediousness out of writing scripts.


    Get Started Today