November 2018 Summaries

In the third installment of a series on deep learning for mobile devices, the article details the process of creating an iPhone app capable of recognizing handwritten numbers using a deep learning network. It starts with training a model on the MNIST dataset, which consists of 28x28 pixel images of handwritten digits, using convolutional neural networks (CNNs) built with Keras. The model is then converted to Apple's CoreML format for deployment on an iPhone. The author explains how to set up the app in XCode, integrate the CoreML model, and utilize the iPhone's camera to capture images for real-time number recognition. The article emphasizes the importance of preprocessing data, model training, and conversion to the CoreML format, while also highlighting potential improvements such as data augmentation and adding a "background" class to enhance model performance. It concludes by suggesting potential applications of computer vision in mobile apps and encourages readers to experiment with the provided code.

Comet.ml enhances the functionality of Jupyter notebooks by providing seamless integration for tracking and visualizing machine learning model results in real time. Jupyter notebooks, widely used by data scientists for their ability to combine code, text, and multimedia, have seen significant growth, with over 2.5 million public notebooks recorded in 2018. Comet.ml offers full support for Jupyter and its extensions, such as JupyterLab and Google Colaboratory, enabling data teams to track datasets, code changes, and experimentation history, thereby improving efficiency, transparency, and reproducibility. The platform's features include instant feedback, low overhead for creating complex plots, easy collaboration, and rich visualizations that allow users to compare results across iterations. Comet.ml positions itself as an essential tool for machine learning operations, comparable to GitHub's impact on software development, and encourages users to explore its capabilities through a sample notebook and a free account.