In the last episode How to master optimisation in deep learning I explained some of the most challenging tasks of deep learning and some methodologies and algorithms to improve the speed of convergence of a minimisation method for deep learning.
I explored the family of gradient descent methods - even though not exhaustively - giving a list of approaches that deep learning researchers are considering for different scenarios. Every method has its own benefits and drawbacks, pretty much depending on the type of data, and data sparsity. But there is one method that seems to be, at least empirically, the best approach so far.
Feel free to listen to the previous episode, share it, re-broadcast or just download for your commute.
In this episode I would like to continue that conversation about some additional strategies for optimising gradient descent in deep learning and introduce you to some tricks that might come useful when your neural network stops learning from data or when the learning process becomes so slow that it really seems it reached a plateau even by feeding in fresh data.
Do you fear of AI? Why? (Ep. 176)
Composable models and artificial general intelligence (Ep. 175)
Ethics and explainability in AI with Erika Agostinelli from IBM (ep. 174)
Is neural hash by Apple violating our privacy? (Ep. 173)
Fighting Climate Change as a Technologist (Ep. 172)
AI in the Enterprise with IBM Global AI Strategist Mara Pometti (Ep. 171)
Speaking about data with Mikkel Settnes from Dreamdata.io (Ep. 170)
Send compute to data with POSH data-aware shell (Ep. 169)
How are organisations doing with data and AI? (Ep. 168)
Don't fight! Cooperate. Generative Teaching Networks (Ep. 167)
CSV sucks. Here is why. (Ep. 166)
Reinforcement Learning is all you need. Or is it? (Ep. 165)
What's happening with AI today? (Ep. 164)
2 effective ways to explain your predictions (Ep. 163)
The Netflix challenge. Fair or what? (Ep. 162)
Artificial Intelligence for Blockchains with Jonathan Ward CTO of Fetch AI (Ep. 161)
Apache Arrow, Ballista and Big Data in Rust with Andy Grove RB (Ep. 160)
GitHub Copilot: yay or nay? (Ep. 159)
Pandas vs Rust [RB] (Ep. 158)
A simple trick for very unbalanced data (Ep. 157)
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
Acquired