Heartbeat Newsletter: Volume 31
Convergence Conference
Dear Heartbeat Readers,
Did you attend Day 1 of our second annual Convergence Conference? We’ve got over 25 speakers and tons of great panels and discussions from leaders in the ML industry. Day 2 kicks off shortly and you can register for live sessions here. Free registration also gives you access to the recordings from previous sessions — you don’t want to miss a thing!
Heartbeat these past few weeks has had lots of great articles covering the latest research, NLP use-cases, and Comet tutorials. And remember that you can join our community Slack to chat with fellow practitioners, ask the Comet ML team questions, and get inspiration for your next project.
Happy Reading,
Emilie, Abby & the Heartbeat Team
Natural Language Processing With SpaCy (A Python Library)
— by Khushboo Kumari
This post goes over how the most cutting-edge NLP software, SpaCy, operates. You will also discover SpaCy’s outstanding attributes and how they differ from NLTK, which offers an intriguing look at NLP.
Things You Can do Using Kangas Library in Data Science
— by Pranjal Saxena
Kangas, developed by the team at Comet, is an open source tool that allows data developers to load, sort, group, and visualize millions of images at once without the risk of crashing their notebooks. Data developers no longer have to worry about the limitations of working with large datasets and can focus on analyzing and interpreting the data.
Transforming a Horse to a Zebra Using A Generative Adversarial Network (GAN)
— by Omale Happiness
In this tutorial, learn how to transform a horse to a zebra using a generative adversarial network, then deploy it as a web application using Streamlit.
Text Classification Using R, Keras, and Comet ML
— by Klurdy Studios
This tutorial will teach you how to train your binary text classifiers using Keras. You will use the IMDB dataset that has 50K+ movie reviews that are classified as positive or negative. The main goal of this tutorial is to equip you with the skills of using R and R Studio to build the classifier while using Comet ML’s platform to monitor your experiments.
An End-to-End Guide on Using Comet ML’s Model Versioning Feature: Part 1
— by Mwanikii
Comet ML has an intricate web of tools that combine simplicity and safety and allows one to not only track changes in their model but also deploy them as desired or share in teams.
Sentiment Analysis With SparkNLP and Comet
— by Jammie Sandy
We will build a pipeline for performing sentiment analysis on text data using the Spark NLP library and use Comet to monitor the metrics of our model. Comet is an online platform that allows you to track and monitor logs experiments and we are using Comet in this tutorial to track the metrics of our model.
Using Deep Learning To Improve the Traditional Machine Learning Performance
— by Edwin Maina
The advent of deep learning has been a game-changer in machine learning, paving the way for the creation of complex models capable of feats previously thought impossible. These models have been used to achieve state-of-the-art performance in many different fields, including image classification, natural language processing, and speech recognition. This article delves into using deep learning to enhance the effectiveness of classic ML models.
A Detailed Beginner’s Guide to Keras Tuner
— by Timothy Lu
A big part of data science is tuning our models and improving upon them over time. But instead of just tuning specific hyperparameters, we can also decide how our network is shaped. In this article, I will go through some basic concepts of creating a neural network using TensorFlow and then explore how we might improve upon our model’s architecture using Keras Tuner.
The Future of Machine Learning: Understanding GANs and DRL
— by Baraka Randy
Deep learning has grown in importance as a focus of artificial intelligence research and development in recent years. Deep Reinforcement Learning (DRL) and Generative Adversarial Networks (GANs) are two promising deep learning trends.
Semi-supervised Deep Learning for Medical Image Segmentation
— by Hritam Basak
In this article we will look into medical image segmentation and see how deep learning can be helpful in these cases. We will also look for the research gaps in this field, which could inspire potential future projects. Finally, we will look at some of the recent semi-supervised medical image segmentation algorithms.
Monitoring A Convolutional Neural Network (CNN) in Comet
— by Oluseye Jeremiah
A convolutional neural network (CNN) is primarily used for image classification. Convolutional, pooling, and fully linked layers are some of the layers that make up a CNN. The pooling layers are used to shrink the spatial dimensions of the image while preserving the key features, whereas the convolutional layers are in charge of identifying patterns and features in the image. The image is subsequently classified using the convolutional and pooling layers’ retrieved features by the fully connected layers.
Image Classification Using R, Keras, and Comet ML
— by Klurdy Studios
Computer vision is an interesting field in machine learning as it helps computers understand what they see. Computer vision has various sub-topics like segmentation, object detection, image synthesis, etc. This tutorial will focus on building image classifiers from the ground up and monitoring the training process.
Text Classification Using Machine Learning Algorithm in R
— by Daniel Tope Omole
Text classification, which involves categorizing text into specified groups based on its content, is an important natural language processing (NLP) task. Text categorization is supported by a number of programming languages, including R, Python, and Weka, but the main focus of this article will be text classification with R.
