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.
True Machine Intelligence just like the human brain (Ep. 155)
Delivering unstoppable data with Streamr (Ep. 154)
MLOps: the good, the bad and the ugly (Ep. 153)
MLOps: what is and why it is important Part 2 (Ep. 152)
MLOps: what is and why it is important (Ep. 151)
Can I get paid for my data? With Mike Andi from Mytiki (Ep. 150)
Building high-growth data businesses with Lillian Pierson (Ep. 149)
Learning and training in AI times (Ep. 148)
You are the product [RB] (Ep. 147)
Polars: the fastest dataframe crate in Rust - with Ritchie Vink (Ep. 146)
Apache Arrow, Ballista and Big Data in Rust with Andy Grove (Ep. 145)
Pandas vs Rust (Ep. 144)
Concurrent is not parallel - Part 2 (Ep. 143)
Concurrent is not parallel - Part 1 (Ep. 142)
Backend technologies for machine learning in production (Ep. 141)
You are the product (Ep. 140)
How to reinvent banking and finance with data and technology (Ep. 139)
What's up with WhatsApp? (Ep. 138)
Is Rust flexible enough for a flexible data model? (Ep. 137)
Is Apple M1 good for machine learning? (Ep.136)
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
Black Wolf Feed (Chapo Premium Feed Bootleg)
Bannon`s War Room