The more I use Deep Learning, the more I am amazed by it. Some things which would be hard to do programmatically are easy with the right Neural Network. It feels like we are just starting to scratch the possibilities.
Walk to Rottingdean
This afternoon we watched along the Under Cliff walk to Rottingdean. It's a walk we've done many times in the past. The tide was fully in, so the waves were crashing over the path in places.
CakeWatch
I'm really enjoying the new (anti)-Brexit Podcast - CakeWatch. Chris Kendall and Steve Bullock deliver a lively discussion on the events of the week. It's amazing how many events around Brexit are happening every week! At the moment I'm listening to the CakeWatch podcast and The Guardian Brexit means... podcast.
End to Veganism?
Helen and I have stopped being mainly vegan - primarily because of milk and cheese. Non-dairy milks are OK for coffee and tea, and work quite well in muesli, but cow milk is so much better! Also, after trying a lot of vegan cheeses, there just is no substitute for dairy cheeses. We are still primarily vegetarian though.
Computation meets Data Science Conference
Today I was at a Computation meets Data Science Conference, organised by Wolfram Research and the CQF. There were some interesting talks. The ones I enjoyed the most used Mathematica to analyse data in real time in interesting ways. It looks like Mathematica has good support for building neural networks now. I was impressed at how quickly Jon Macloone from Wolfram was able to get some quite useful neural network models up and running. Jon made the point that for some problems you are able to get results really quickly with neural nets, and others it's really hard to get good results, and it's not obvious which problems are which.