Flock & Dapr: Resilient Cloud-Native Agent Swarms Contents What is Dapr? Why we built this integration The integration surface is small One workflow, three backends One-time setup In-memory: the local baseline PostgreSQL: durable and transactional Redis encrypted: hardened for cloud-native deployment Capabilities, not promises Why this matters Dapr or [...]
What's all the hype with Transformers? Part 3: Enter the Transformer Model In our previous posts "What’s all the Hype with Transformers? The Trouble with Natural Language Processing" and "What’s all the hype with Transformers? Part 2: Memory for RNNs", we highlighted some of the issues of natural language [...]
What's all the hype with Transformers? Part 2: Memory for RNNs Contents Introduction Recurrent Neural Networks Towards a Solution: Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) Introduction In the previous post, we highlighted some of the issues we are faced with when attempting to process natural language [...]
What's all the Hype with Transformers? The Trouble with Natural Language Processing Contents Introduction The Troubles with Natural Language Processing Traditional Neural Networks Recurrent Neural Networks Outlook Introduction This post tries to highlight the practical differences between traditional RNNs and the new Transformer Architecture. We are not going to [...]