Posts

Harnessing Lineage for Continuous Improvement in your Deep Learning Datasets

In the world of deep learning, the foundation of model success rests upon the datasets they are trained on. These datasets act as the lifeblood of machine learning applications for solving real world problems. While both supervised and unsupervised datasets play crucial role in shaping the capabilities of deep learning models, it’s the supervised datasets that stand out as the gold standard for achieving robust and reliable performance. These datasets come armed with meticulously and usually human labelled ground truth, guiding the models towards precision.

September 1, 2023 Read

SEEM: Segment Everything Everywhere All at Once

Coming Soon . . .

June 25, 2023 Read

Segment Anything (SAM)

Coming Soon . . .

June 25, 2023 Read

Deep Learning Algorithms - Applied

Coming Soon . . . Regular posts about new deep learning algorithms applied to real world problems. Deep dive into model architecture. Performance considerations and software architecture for optimal applications.

May 31, 2023 Read

From Chaos to Clarity: How Immutable Data Simplifies Machine Learning Data Storage

Karpathy’s data engine concept is a data management strategy designed to simplify the process of working with large and complex datasets in machine learning applications. Potentially nitpicky but competitive advantage in AI goes not so much to those with data but those with a data engine: iterated data aquisition, re-training, evaluation, deployment, telemetry. And whoever can spin it fastest. Slide from Tesla to ~illustrate but concept is general pic.twitter.com/6O2KxZBg17 — Andrej Karpathy (@karpathy) December 5, 2022 Developed by Andrej Karpathy, former Director of AI at Tesla, the data engine concept aims to streamline the process of data collection, preprocessing, and transformation, allowing machine learning practitioners to focus on the development and deployment of their models.

March 20, 2023 Read

Data Engine - Infrastructure for Software 2.0

Coming Soon . . .

January 8, 2022 Read

Democratise your Data Lake with FastAPI and Cassandra

Motivation A data platform can be thought of as a scalable system for ingestion, curation, transformation and integration of datasets. But the value of a data platform is realised when these datasets are made available for use outside the platform to drive decisions and shape the customer experience, i.e. by democratising the data. Data Democratisation may come in many shapes and sizes, with efforts typically starting with a Data Warehouse exposed via a BI framework (e.

August 10, 2020 Read

Sustainable Growth and Tech. Debt

Any technology-driven organisation that has successfully grown over a long time, would have done so by a mix of visionary leadership, luck and rapidly developing solutions for real-world problems. They would have, along the way, made technical concessions in the solutions they devised. They would have pivoted from experiments and products brought to market. They would have made decisions without knowing what the future holds, decisions motivated by growth, speed or plain survival.

July 24, 2020 Read