Jon Wood has another great video teaching you how to how to use ML.NET to perform transfer leaning from the Inception model built in Tensorflow.
TensorFlow Developer Advocate, Robert Crowe, we’re asking the question, “What exactly is this TFX thing?”
In this video, learn about the TensorFlow.js ecosystem: how to bring an existing ML model into your JS app and re-train the model using your data. We’ll also go over our efforts beyond the browser to bring ML to platforms such as React Native, Raspberry Pi, and Electron.
For more information, check out the accompanying blog post.
In this video, deeplizard explores how to use TensorBoard to visualize metrics of our PyTorch CNN during training process.
Generative models, commonly referred to as GANs, are a family of AI architectures whose aim is to create data samples from scratch. They work by capturing the data distributions of the type of things we want to generate.
Here’s an interesting read on the topic.
These kind of models are being heavily researched, and there is a huge amount of hype around them. Just look at the chart that shows the numbers of papers published in the field over the past few years:
This talk from io19 is for people who know how to code, but who don’t necessarily know machine learning.
Watch this video to learn the ‘new’ paradigm of machine learning, and how models are an alternative implementation for some logic scenarios, as opposed to writing if/then rules and other code.
Chances are that you already know what TensforFlow is and why it’s important. However, as AI spreads from the lab to data science departments and into production, tools like TensorFlow will start crossing paths with the rest of enterprise IT.
TechRebublic has details on a free ebook on TensorFlow: a Guide for IT Pros.
TensorFlow is an open source software library developed by Google for numerical computation with data flow graphs. It offers tremendous opportunities for developers building machine learning into their products. This ebook looks at what TensorFlow is, where it’s headed, and how it’s being put to work.
LinkedIn has just open sourced a tool it created to convert Apache Spark-based big data into a format that can be readily consumed by TensorFlow. The tool, Avro2TF “bridges the gap and presents an elegant solution for ML engineers, freeing them up to focus on different deep learning algorithms,” the team stated.
The team noted that like LinkedIn, many other companies have vast amounts of ML data in a similar sparse vector format, and Tensor format is still relatively new to many of them. The believe that Avro2TF can help address these challenges.
It’s interesting to see LinkedIn, which itself is owned by Microsoft, open source their internal AI/ML tooling, joining the likes of Uber, Facebook, etc. What a time to be alive! 🙂