GPT2 using Mathematica and MXNet

A large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.

Topology and business

Nothing as applicable as an abstract theory. Topology might seem abstract and foundational (like number theory) but has a wide range of applications in life. The combination of topology and data science, in particular, is called topological…

Cirq tutorial

Google's Cirq is a Python SDK to perform quantum simulations.

Advanced topics in deep reinforcement learning

Part of a large set of lectures on deep reinforcement learning by DeepMind.

Research directions in quantum computing

The four main research channels in quantum computing.

What is persistent homology?

About topological data analysis and persistent homology in particular.

Apache Jena disaster

Jena and Fuseki are not reliable.

Grakn has something new and exciting but not yet ready for prime time.

Graph nets

Learning from graphs rather than from tabular data.

Cross validated predictions

Crossval predictions instead of the usual fit-predict approach.