Insights
Engineering Insights
Practical writing on software architecture, SaaS products, AI automation, legacy modernisation, and the business of building reliable systems.
Curated links from external sources — not 360Softy original articles.
Dota 2 with large scale deep reinforcement learning
Update on the State of Prisma 2 (December 2019)
Get the December 2019 Prisma 2 roadmap update, including timeline changes and expected production-ready releases.
Deep double descent
We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or training time. This effect is often avoided through careful regularization. While this behavior appears to be fairly universal, we don’t yet fully understand why it happens, and view further study of this phenomenon as an important research direction.
Work with 360Softy
Building a SaaS product, AI system, or business platform?
Book a free consultation and we will tell you honestly whether we can help.