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 58: There is physics in deep learning!
Episode 57: Neural networks with infinite layers
Episode 56: The graph network
Episode 55: Beyond deep learning
Episode 54: Reproducible machine learning
Episode 53: Estimating uncertainty with neural networks
Episode 52: why do machine learning models fail? [RB]
Episode 51: Decentralized machine learning in the data marketplace (part 2)
Episode 50: Decentralized machine learning in the data marketplace
Episode 49: The promises of Artificial Intelligence
Episode 48: Coffee, Machine Learning and Blockchain
Episode 47: Are you ready for AI winter? [Rebroadcast]
Episode 46: why do machine learning models fail? (Part 2)
Episode 45: why do machine learning models fail?
Episode 44: The predictive power of metadata
Episode 43: Applied Text Analysis with Python (interview with Rebecca Bilbro)
Episode 42: Attacking deep learning models (rebroadcast)
Episode 41: How can deep neural networks reason
Episode 40: Deep learning and image compression
Episode 39: What is L1-norm and L2-norm?
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