Digests » 146


Make all your Python code more readable with Sourcery

It’s not just bugs that slow down projects - code that’s too complex or hard to understand can slow you and your team down. Sourcery gives you instant refactoring suggestions while you work in your IDE to help make your code easier to understand and easier to work with.

this week's favorite

Multimodal Neurons in Artificial Neural Networks

We’ve discovered neurons in CLIP that respond to the same concept whether presented literally, symbolically, or conceptually. This may explain CLIP’s accuracy in classifying surprising visual renditions of concepts, and is also an important step toward understanding the associations and biases that CLIP and similar models learn.

Backyard Birdbot

The aim of the project is to use existing ML models to first detect birds then classify what species it belongs to. We won't be training any new models here. For object detection, we use the SSD Openimages v4 model published as part of TensorFlow Object Detection API.

How AI from Bing is powering Azure Cognitive Search

Azure Cognitive Search is a cloud search service that gives developers APIs and tools to build rich search experiences over private, heterogeneous content in web, mobile, and enterprise applications. It has multiple components, including an API for indexing and querying, seamless integration through Azure data ingestion, deep integration with Azure Cognitive Services, and persistent storage of user-owned indexed content.

Understanding Deep Learning (Still) Requires Rethinking Generalization

Despite their massive size, successful deep artificial neural networks can exhibit a remarkably small gap between training and test performance. Conventional wisdom attributes small generalization error either to properties of the model family or to the regularization techniques used during training.

Generative Speech Coding with Predictive Variance Regularization

The recent emergence of machine-learning based generative models for speech suggests a significant reduction in bit rate for speech codecs is possible. However, the performance of generative models deteriorates significantly with the distortions present in real-world input signals.