Category: Machine Learning

Pete Warden explains a phenomenon:

One of the most frequent questions I get asked from people exploring machine learning beyond cloud and desktop machines is “What about training?”. If you look around at the popular frameworks and use cases of edge ML, most of them seem focused on inference. It isn’t obvious why this is the case though, so I decided to collect my notes in a post here, so I can have something to refer to when this comes up (and organize my own thoughts too!).

Pete’s reasons make sense. I think the last one is the most important.

Comments closed

Hangfei Lin and Jinghui Mo make an announcement:

We’re excited to announce today that Feathr is joining LF AI & Data, the Linux Foundation’s umbrella foundation supporting open source innovation in artificial intelligence (AI) and data. Feathr is a feature store that simplifies machine learning (ML) feature serving and improves developer productivity.

“We’re excited to welcome Feathr to LF AI & Data and for it to be part of our technical project portfolio (41 projects and growing) with a community of over 17K developers,” said Dr. Ibrahim Haddad, Executive Director of LF AI & Data. “We aim to support Feathr to expand its user base, grow its community of developers, become a leader within its own category, and enable collaboration and integration opportunities with other projects. We look forward to the project’s continued growth and success as part of LF AI & Data.”

Alex Woodie has more background:

Feathr was originally developed at LinkedIn to help manage and serve features used in its machine learning applications. Instead of manually working with features as part of an individual data pipeline, Feathr automates and standardizes the interaction with the data type, which is used in both the training and inference stages of machine learning.

Comments closed

Jason Brownlee takes us through three common classes of neural network and explains when each is useful:

In this post, you will discover the suggested use for the three main classes of artificial neural networks.

After reading this post, you will know:

– Which types of neural networks to focus on when working on a predictive modeling problem.

– When to use, not use, and possible try using an MLP, CNN, and RNN on a project.

– To consider the use of hybrid models and to have a clear idea of your project goals before selecting a model.

Read the whole thing.

Comments closed

John Mount is not impressed with a fair amount of machine learning:

For this to actually happen we need the actual system to be in our concept space, a lot of training data, and an abundance of caution.

In practice what we see more and more is the training procedure in fact attacks the evaluation procedure. It doesn’t just improve the quality of the fit artifact, but through mere optimization accidentally exploits weaknesses in the measurement system itself. When this happens, fitting does the following.

In ML training, we often accidentally “teach to the test” by comparing models via test data, which over time selects for models which are better fits for the test data. As John notes, this can come two separate ways and if you don’t define your optimization strategy correctly, you can accidentally train models which optimize on non-realistic things. A classic example is the neural network which could pick out malignant tumors from non-malignant tumors not because of any property of the tumor itself but rather because the malignant tumor images all had rulers in them and the non-malignant images did not. Read the whole thing for a second pitfall you can hit when training models.

Comments closed