Continuing the discussion of the last two episodes, there is one more aspect of deep learning that I would love to consider and therefore left as a full episode, that is parallelising and distributing deep learning on relatively large clusters.
As a matter of fact, computing architectures are changing in a way that is encouraging parallelism more than ever before. And deep learning is no exception and despite the greatest improvements with commodity GPUs - graphical processing units, when it comes to speed, there is still room for improvement.
Together with the last two episodes, this one completes the picture of deep learning at scale. Indeed, as I mentioned in the previous episode, How to master optimisation in deep learning, the function optimizer is the horsepower of deep learning and neural networks in general. A slow and inaccurate optimisation method leads to networks that slowly converge to unreliable results.
In another episode titled “Additional strategies for optimizing deeplearning” I explained some ways to improve function minimisation and model tuning in order to get better parameters in less time. So feel free to listen to these episodes again, share them with your friends, even re-broadcast or download for your commute.
While the methods that I have explained so far represent a good starting point for prototyping a network, when you need to switch to production environments or take advantage of the most recent and advanced hardware capabilities of your GPU, well... in all those cases, you would like to do something more.
Episode 38: Collective intelligence (Part 2)
Episode 38: Collective intelligence (Part 1)
Episode 37: Predicting the weather with deep learning
Episode 36: The dangers of machine learning and medicine
Episode 35: Attacking deep learning models
Episode 34: Get ready for AI winter
Episode 33: Decentralized Machine Learning and the proof-of-train
Episode 32: I am back. I have been building fitchain
Founder Interview – Francesco Gadaleta of Fitchain
Episode 31: The End of Privacy
Episode 30: Neural networks and genetic evolution: an unfeasible approach
Episode 29: Fail your AI company in 9 steps
Episode 28: Towards Artificial General Intelligence: preliminary talk
Episode 27: Techstars accelerator and the culture of fireflies
Episode 26: Deep Learning and Alzheimer
Episode 25: How to become data scientist [RB]
Episode 24: How to handle imbalanced datasets
Episode 23: Why do ensemble methods work?
Episode 21: Additional optimisation strategies for deep learning
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
The Unbelivable Truth - Series 1 - 26 including specials and pilot
Lex Fridman Podcast