|
|
|
|
Editor Picks
- Lara's Storytelling Resources
Here is a non-exhaustive list of various resources you might want if you're interested in automated story generation, interactive fiction (IF), or related research areas (such as tabletop roleplaying games—TRPGs). This list was first created when I co-taught Interactive Fiction and Text Generation at UPenn with Chris Callison-Burch. Note: This is not a list of papers in the field, but rather a list of databases and code and their corresponding papers...
- The Importance of Data Splitting [Interactive Explanation]
In most supervised machine learning tasks, best practice recommends to split your data into three independent sets: a training set, a testing set, and a validation set...To learn why, let's pretend that we have a dataset of two types of pets: Cats and Dogs...Each pet in our dataset has two features: weight and fluffiness...Our goal is to identify and evaluate suitable models for classifying a given pet as either a cat or a dog. We'll use train/test/validations splits to do this!...
A Message from this week's Sponsor:
Retool is the fast way to build an interface for any database
With Retool, you don't need to be a developer to quickly build an app or dashboard on top of any data set. Data teams at companies like NBC use Retool to build any interface on top of their data—whether it's a simple read-write visualization or a full-fledged ML workflow.
Drag and drop UI components—like tables and charts—to create apps. At every step, you can jump into the code to define the SQL queries and JavaScript that power how your app acts and connects to data. The result—less time on repetitive work and more time to discover insights.
Data Science Articles & Videos
- Bandits for Recommender Systems
Recommender systems work well when we have a lot of data on user-item preferences. With a lot of data, we have high certainty about what users like. Conversely, with very little data, we have low certainty. Despite the low certainty, recommenders tend to greedily promote items that received higher engagement in the past. And because they influence how much exposure an item gets, potentially relevant items that aren’t recommended continue getting no to low engagement, perpetuating the feedback loop...Bandits address this by modeling uncertainty and exploration....
- How Should you Protect your Machine Learning Models and IP?
I’ve helped hundreds of product teams ship ML-based products, inside and outside of Google, and one of the most frequent questions I got was “How do I protect my models?”...This worry is completely understandable, because modern machine learning has become essential for many applications so quickly that best practices haven’t had time to settle and spread. The answers are complex and depend to some extent on your exact threat models, but if you want a summary of the advice I usually give it boils down to...
- A Generalist Agent
Inspired by progress in large-scale language modelling, we apply a similar approach towards building a single generalist agent beyond the realm of text outputs. The agent, which we refer to as Gato, works as a multi-modal, multi-task, multi-embodiment generalist policy. The same network with the same weights can play Atari, caption images, chat, stack blocks with a real robot arm and much more, deciding based on its context whether to output text, joint torques, button presses, or other tokens. In this report we describe the model and the data, and document the current capabilities of Gato...
- A Tutorial on Structural Optimization
Structural optimization is a useful and interesting tool. Unfortunately, it can be hard to get started on the topic because existing tutorials assume the reader has substantial domain knowledge. They obscure the fact that structural optimization is really quite simple, elegant, and easy to implement...With that in mind, let’s write our own structural optimization code, from scratch, in 180 lines...
- Beyond Message Passing: a Physics-Inspired Paradigm for Graph Neural Networks
The message-passing paradigm has been the “battle horse” of deep learning on graphs for several years, making graph neural networks a big success in a wide range of applications...We argue that the “node and edge-centric” mindset of current graph deep learning schemes imposes strong limitations that hinder future progress in the field. As an alternative, we propose physics-inspired “continuous” learning models that open up a new trove of tools from the fields of differential geometry, algebraic topology, and differential equations so far largely unexplored in graph ML....
- Neo: Hierarchical Confusion Matrix
The confusion matrix, a ubiquitous visualization for helping people evaluate machine learning models, is a tabular layout that compares predicted class labels against actual class labels over all data instances. Neo is a visual analytics system that enables practitioners to flexibly author and interact with hierarchical and multi-output confusion matrices, visualize derived metrics, renormalize confusions, and share matrix specifications....
- Automatic Differentiation: Forward and Reverse
Deriving derivatives is not fun. In this post, I will deep dive into the methods for automatic differentiation (abbreviated as AD by many). After reading this post, you should feel confident with using the various AD techniques, and hopefully never manually calculate derivatives again...
- Practical Machine Learning and Deep learning
Podcast interview of Sebastian Raschka, lead author of a new book from Packt entitled “Machine Learning with PyTorch and Scikit-Learn” and an Assistant Professor of Statistics at the University of Wisconsin (Madison), on the state of tools for training, tuning, and evaluating machine learning models...We discuss resources and libraries available to developers & software engineers who want to start using and deploying machine learning and deep learning...
- Historical Thoughts on Modern Prediction [Video]
I’ll tell a history of statistical prediction, beginning with Wiener and Rosenblatt and ending with contemporary machine learning. This will highlight the cyclical rediscovery of pattern recognition and subsequent disillusionment with its shortcomings. I will describe how our theoretical understanding of statistical learning has not deepened for over half a century. I will trace how the empirical standards of the field arose from technological and social developments, many of which transpired in Palo Alto in the 1960s...
Conference*
Join us at apply(), the ML data engineering conference - it’s free.
Only one week left to register! Speakers include practitioners from the Wikimedia Foundation, Facebook, Snapchat, Stripe, a16z, Databricks, and more.
Agenda highlights:
- Chris Albon, Director of Machine Learning at Wikimedia Foundation: More Ethical Machine Learning Using Model Card at Wikimedia
- Matei Zaharia, Co-Founder and Chief Technologist at Databricks: The Future of Data for Machine Learning
- Clem Delangue, CEO at Hugging Face: Is Open-Source Machine Learning Becoming the Most Impactful Technology of the Decade?
We’ll also host hands-on workshops to experience MLOps tools in action, as well as in-person meetups in NYC and SF!
See the full agenda and register for free.
*Sponsored post. If you want to be featured here, or as our main sponsor, contact us!
Jobs
- Data Scientist - Hungryroot - Remote
Hungryroot is looking for a Data Scientist to join our growing Data Team. As a Data Scientist, you will work closely with other Data Scientists and Data Engineers to develop various Machine Learning models that power Hungryroot and it’s AI functions. These models include traditional forecasting models, as well as more industry-specific optimization challenges.
As a Data Scientist at Hungryroot, you will work on answering questions like: how do you tell what food someone would like to eat this week, how do you determine whether they enjoyed it or not, maybe they liked their means last week, but are now looking for different options, maybe they like the same food on Tuesdays, but variety on Fridays, what about spicy food, is Green Chilly as spicy as Green Curry?
Want to post a job here? Email us for details --> team@datascienceweekly.org
Training & Resources
- Data Visualization with D3 – Full Course for Beginners [2022]
Learn data visualization with D3.js. D3 is a JavaScript library for manipulating documents based on data. D3 helps you bring data to life using HTML, SVG, and CSS...This course is an edited collection of live streams taught by Dr. Curran Kelleher. He is one of the top D3 instructors in the world. He has a Ph.D. in Computer Science, and has taught at universities including MIT...
Books
-
Integrate scikit-learn with various tools such as NumPy, pandas, imbalanced-learn, and scikit-surprise and use it to solve real-world machine learning problems...
For a detailed list of books covering Data Science, Machine Learning, AI and associated programming languages check out our resources page.
P.S., Enjoy the newsletter? Please forward it to your friends and colleagues - we'd love to have them onboard :) All the best, Hannah & Sebastian
|
|
|
|
|
