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.
The Power of Graph Neural Networks: Understanding the Future of AI - Part 1/2 (Ep.223)
Leveling Up AI: Reinforcement Learning with Human Feedback (Ep. 222)
The promise and pitfalls of GPT-4 (Ep. 221)
AI’s Impact on Software Engineering: Killing Old Principles? (Ep. 220)
Edge AI applications for military and space [RB] (Ep. 219)
Prove It Without Revealing It: Exploring the Power of Zero-Knowledge Proofs in Data Science (Ep. 218)
Deep learning vs tabular models (Ep. 217)
[RB] Online learning is better than batch, right? Wrong! (Ep. 216)
Chatting with ChatGPT: Pros and Cons of Advanced Language AI (Ep. 215)
Accelerating Perception Development with Synthetic Data (Ep. 214)
Edge AI applications for military and space [RB] (Ep. 213)
From image to 3D model (Ep. 212)
Machine learning is physics (Ep. 211)
Autonomous cars cannot drive. Here is why. (Ep. 210)
Evolution of data platforms (Ep. 209)
[RB] Is studying AI in academia a waste of time? (Ep. 208)
Private machine learning done right (Ep. 207)
Edge AI for applications in military and space (Ep. 206)
[RB] What are generalist agents and why they can change the AI game (Ep. 205)
LIDAR, cameras and autonomous vehicles (Ep. 204)
Create your
podcast in
minutes
It is Free
Insight Story: Tech Trends Unpacked
Zero-Shot
Fast Forward by Tomorrow Unlocked: Tech past, tech future
Lex Fridman Podcast
The Unbelivable Truth - Series 1 - 26 including specials and pilot