Possibly some scenarios in RL where online learning is involved
HN user
aiwabdn
Main reason for now is that the cosine similarity used as context function is not suitable for natural images like those in Imagenet. We are experimenting some extensions based on convolutions for such use cases.
This blog post details our interpretation of Gated Linear Networks, a new family of neural networks proposed by researchers at DeepMind. Implementations in JAX, NumPy, PyTorch and Tensorflow are here: https://github.com/aiwabdn/pygln
- We have come up with implementations of GLN from the paper in NumPy, PyTorch, TensorFlow and JAX. Check it out here: https://github.com/aiwabdn/pygln - Comments, feedback, pointers, use-case suggestions are all very welcome :)
I moved to London from India to do a masters and then found a job. The market definitely tries to capitalise on the visa requirement. They will try to get you at lower salaries, £40-50k. That being said, comparing it with the US market is quite unfair. At £50k you will have a comfortable life. But given you have 10 years of experience, you should definitely push for more. The other option would be to move here and find a better paying job.