Federated Learning 101 with FEDn
Training good machine learning models requires access to good data. The problem is that most of the data in the world is not accessible to use when training machine learning models. Data cannot be moved or shared based on privacy concerns, regulatory constraints, or infrastructural reasons.... Read more
Emerging Hotspot Analysis As a Tool For Quantifying Spatial-Temporal Patterns of Deforestation
Geospatial point patterns such as deforestation, crime, disease occurrence, and fires (among others) change across space and time. Identifying how a given geospatial phenomenon has changed over time and space can provide valuable insights into both past and emerging trends, changing landscapes and contexts. While spatial... Read more
Audio-Visual Speech Enhancement and Separation Based on Deep Learning
Imagine being at a cocktail party with your friends. Although you are surrounded by other people having their own conversations and a music band is playing in the background, you are still able to engage with your friends and understand what they are saying. The reason... Read more
Saying Hello to DataFrames.jl
A majority of data scientists use Python or R to perform data preparation tasks before jumping to modeling. The Julia language is a younger player in this field that promises that you will be able to do the number-crunching-intensive parts of your pipelines fast. However, the... Read more
Model Governance: A Checklist for Getting AI Safely to Production
Putting AI models into production is notoriously difficult—and research reflects that. A NewVantage Partners survey found that the percentage of firms investing greater than $50 million in Big Data and AI initiatives is up to 64.8%, with a total of 98.8% of firms investing. Despite this,... Read more
Auto-Sklearn: AutoML in Python
Machine learning is the driving force of modern technology and smart applications. While highly efficient methods and implementations are broadly available, their successful application is hard. It is hard because a myriad of design decisions have to be made correctly before an ML pipeline achieves peak... Read more
Announcing the ODSC Europe 2021 Keynotes
We’re happy to announce the ODSC Europe 2021 Keynotes – leaders in applied AI from Europe who will kick off the already expert lineup set to speak at the community-based event for data science practitioners and AI engineers. These academics, innovators, and thought leaders are leading... Read more
Final ODSC Europe 2021 Schedule Released! See it Here
ODSC Europe Virtual is only a few weeks away, coming this June 8th-10th, and it’s time to start planning which talks, workshops, and training sessions you’ll be attending. So pull up your calendar and clear some time to check out the just-released full ODSC Europe 2021... Read more
Never Wait for a Job to Start Working in Data Science
You finally finished that college CS degree, completed hundreds of hours of training online, got your certifications, or simply have the skills you need to transition. The bottom line is, you are ready to start working in data science, an incredibly exciting field. And then, you... Read more
Adversarial Image Explanation Through Alibi
Deep learning-based computer vision has plenty of real-life applications. In particular, Convolutional Neural Network (CNN) architectures are commonly used across multiple CV tasks as they have high accuracy. But their strength leads also to a weakness point, as a little perturbation to an input image/frame can... Read more