Remove 2019 Remove Deep Learning Remove Statistics Remove Testing
article thumbnail

SiftSeq: Classifying short DNA sequences with deep learning

Insight

In this post, I demonstrate how deep learning can be used to significantly improve upon earlier methods, with an emphasis on classifying short sequences as being human, viral, or bacterial. As I discovered, deep learning is a powerful tool for short sequence classification and is likely to be useful in many other applications as well.

article thumbnail

Why you should care about debugging machine learning models

O'Reilly on Data

In addition to newer innovations, the practice borrows from model risk management, traditional model diagnostics, and software testing. Because ML models can react in very surprising ways to data they’ve never seen before, it’s safest to test all of your ML models with sensitivity analysis. [9]

Insiders

Sign Up for our Newsletter

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Trending Sources

article thumbnail

What you need to know about product management for AI

O'Reilly on Data

Pragmatically, machine learning is the part of AI that “works”: algorithms and techniques that you can implement now in real products. We won’t go into the mathematics or engineering of modern machine learning here. Machine learning adds uncertainty. Managing Machine Learning Projects” (AWS).

article thumbnail

Adding Common Sense to Machine Learning with TensorFlow Lattice

The Unofficial Google Data Science Blog

On the one hand, basic statistical models (e.g. On the other hand, sophisticated machine learning models are flexible in their form but not easy to control. Curiosities and anomalies in your training and testing data become genuine and sustained loss patterns. Other deep learning models can also be written in this form.

article thumbnail

Themes and Conferences per Pacoid, Episode 9

Domino Data Lab

For example, in the case of more recent deep learning work, a complete explanation might be possible: it might also entail an incomprehensible number of parameters. They also require advanced skills in statistics, experimental design, causal inference, and so on – more than most data science teams will have.

article thumbnail

7 Powerful Open Source Tools For Your Data Projects

Smart Data Collective

Ludwig is a tool that allows people to build data-based deep learning models to make predictions. In September 2019, Google decided to make it’s Differential Privacy Library available as an open-source tool. Also, if you’re not strong in statistics yet, no problem — let Jamovi act as your introductory tool.

article thumbnail

Themes and Conferences per Pacoid, Episode 7

Domino Data Lab

O’Reilly Media published our analysis as free mini-books: The State of Machine Learning Adoption in the Enterprise (Aug 2018). Evolving Data Infrastructure: Tools and Best Practices for Advanced Analytics and AI (Jan 2019). AI Adoption in the Enterprise: How Companies Are Planning and Prioritizing AI Projects in Practice (Feb 2019).