Deep Learning with Go
summary
Claims that you can train and deploy deep networks in Go but current reality is mixed: TensorFlow Go partial support lets trained Python graphs run in production but full training in Go is limited; community projects like Gorgonia / go-neural libraries and Machine Box Go SDK provide usable models and APIs. Training demands millions of labeled records (serious work) and large compute; GANs are presented as a practical way to augment data. Examples show deployment works; native Go training is possible but still early.
AI-written summary · about
chapters (5)
- 0:00Intro
- 1:29F-22 RAPTOR
- 11:10SOLVING COMPLEX PROBLEMS
- 23:50EACH NEURON
- 36:53AND THE ROLE OF GO IN ITS ECOSYSTEM
related talks
26mDeep learning in Go - Present and future
04mGo and data, can they ever be friends?
04mTensorFlow and Go
31mMachine Learning for Gophers
29mLearn Neural Networks With Go, Not Math
33mLearn Neural Networks With Go - Not Math!
06mLearn Neural Networks With Go—Not Math! (Interview)
28mBuilding AI Applications in Go