computer science

True Machine Intelligence just like the human brain (Ep. 155)

In this episode I have a really interesting conversation with Karan Grewal, member of the research staff at Numenta where he investigates how biological principles of intelligence can be translated into silicon.We speak about the thousand brains theory and why neural networks forget.
 
 
References
Main paper on the Thousand Brains Theory: https://www.frontiersin.org/articles/10.3389/fncir.2018.00121/full
Blog post on Thousand Brains Theory: https://numenta.com/blog/2019/01/16/the-thousand-brains-theory-of-intelligence/
GLOM paper by Geoff Hinton: https://arxiv.org/pdf/2102.12627.pdf
Why neural networks forget? https://numenta.com/blog/2021/02/04/why-neural-networks-forget-and-lessons-from-the-brain
 

Polars: the fastest dataframe crate in Rust - with Ritchie Vink (Ep. 146)

In this episode I speak with Ritchie Vink, the author of Polars, a crate that is the fastest dataframe library at date of speaking :) If you want to participate to an amazing Rust open source project, this is your change to collaborate to the official repository in the references.
 
References
https://github.com/ritchie46/polars
 

Apache Arrow, Ballista and Big Data in Rust with Andy Grove (Ep. 145)

Do you want to know the latest in big data analytics frameworks? Have you ever heard of Apache Arrow? Rust? Ballista? In this episode I speak with Andy Grove one of the main authors of Apache Arrow and Ballista compute engine.Andy explains some challenges while he was designing the Arrow and Ballista memory models and he describes some amazing solutions.
 
Our Sponsors
This episode is supported by Chapman’s Schmid College of Science and Technology, where master’s and PhD students join in cutting-edge research as they prepare to take the next big leap in their professional journey.To learn more about the innovative tools and collaborative approach that distinguish the Chapman program in Computational and Data Sciences, visit chapman.edu/datascience
 
If building software is your passion, you’ll love ThoughtWorks Technology Podcast. It’s a podcast for techies by techies. Their team of experienced technologists take a deep dive into a tech topic that’s piqued their interest — it could be how machine learning is being used in astrophysics or maybe how to succeed at continuous delivery.
 
References
 
https://arrow.apache.org/
 
https://ballistacompute.org/
 
https://github.com/ballista-compute/ballista
 
 
 
 

Pandas vs Rust (Ep. 144)

Pandas is the de-facto standard for data loading and manipulation. Python is the de-facto programming language for such operations. Rust is the underdog. Or is it?In this episode I am showing you why that is no longer the case.
 
Our Sponsors
This episode is supported by Chapman’s Schmid College of Science and Technology, where master’s and PhD students join in cutting-edge research as they prepare to take the next big leap in their professional journey.To learn more about the innovative tools and collaborative approach that distinguish the Chapman program in Computational and Data Sciences, visit chapman.edu/datascience
 
Amethix use advanced Artificial Intelligence and Machine Learning to build data platforms and predictive engines in domain like finance, healthcare, pharmaceuticals, logistics, energy. Amethix provide solutions to collect and secure data with higher transparency and disintermediation, and build the statistical models that will support your business.  
 
Useful Links
https://github.com/haixuanTao/Data-Manipulation-Rust-Pandas
https://github.com/ritchie46/polars
https://github.com/rust-ndarray/ndarray
 

Concurrent is not parallel - Part 2 (Ep. 143)

In plain English, concurrent and parallel are synonyms. Not for a CPU. And definitely not for programmers. In this episode I summarize the ways to parallelize on different architectures and operating systems.
Rock-star data scientists must know how concurrency works and when to use it IMHO.
 
Our Sponsors
This episode is supported by Chapman’s Schmid College of Science and Technology, where master’s and PhD students join in cutting-edge research as they prepare to take the next big leap in their professional journey.To learn more about the innovative tools and collaborative approach that distinguish the Chapman program in Computational and Data Sciences, visit chapman.edu/datascience
 
Amethix use advanced Artificial Intelligence and Machine Learning to build data platforms and predictive engines in domain like finance, healthcare, pharmaceuticals, logistics, energy. Amethix provide solutions to collect and secure data with higher transparency and disintermediation, and build the statistical models that will support your business.  
 
Useful Links
http://web.mit.edu/6.005/www/fa14/classes/17-concurrency/
https://doc.rust-lang.org/book/ch16-00-concurrency.html
https://urban-institute.medium.com/using-multiprocessing-to-make-python-code-faster-23ea5ef996ba
 

Concurrent is not parallel - Part 1 (Ep. 142)

In plain English, concurrent and parallel are synonyms. Not for a CPU. And definitely not for programmers. In this episode I summarize the ways to parallelize on different architectures and operating systems. Rock-star data scientists must know how concurrency works and when to use it IMHO.
 
Our Sponsors
This episode is supported by Chapman’s Schmid College of Science and Technology, where master’s and PhD students join in cutting-edge research as they prepare to take the next big leap in their professional journey.To learn more about the innovative tools and collaborative approach that distinguish the Chapman program in Computational and Data Sciences, visit chapman.edu/datascience
 
Amethix use advanced Artificial Intelligence and Machine Learning to build data platforms and predictive engines in domain like finance, healthcare, pharmaceuticals, logistics, energy. Amethix provide solutions to collect and secure data with higher transparency and disintermediation, and build the statistical models that will support your business.  
 
 

Is Rust flexible enough for a flexible data model? (Ep. 137)

In this podcast I get inspired by Paul Done's presentation about The Six Principles for Building Robust Yet Flexible Shared Data Applications, and show how powerful of a language Rust is while still maintaining the flexibility of less strict languages.
 
Our Sponsor
This episode is supported by Chapman’s Schmid College of Science and Technology, where master's and PhD students join in cutting-edge research as they prepare to take the next big leap in their professional journey. To learn more about the innovative tools and collaborative approach that distinguish the Chapman program in Computational and Data Sciences, visit chapman.edu/datascience
 

Is Apple M1 good for machine learning? (Ep.136)

In this episode I explain the basics of computer architecture and introduce some features of the Apple M1
Is it good for Machine Learning tasks?
 
References
Computer architectures book https://www.amazon.com/Computer-Architecture-Quantitative-John-Hennessy/dp/012383872X
Performance https://nod.ai/comparing-apple-m1-with-amx2-m1-with-neon/

Rust and deep learning with Daniel McKenna (Ep. 135)

In this episode I speak with Daniel McKenna about Rust, machine learning and artificial intelligence.
You can find Daniel from
http://github.com/xd009642 
https://twitter.com/xd009642
 
Don't forget to come join me in our Discord channel speaking about all things data science.
Subscribe to the official Newsletter and never miss an episode

Scaling machine learning with clusters and GPUs (Ep. 134)

Let's finish this year with an amazing episode about scaling ML with clusters and GPUs. Kind of as a continuation of Episode 112 I have a terrific conversation with Aaron Richter from Saturn Cloud about, well, making ML faster and scaling it to massive infrastructure.
Aaron can be reached on his website https://rikturr.com and Twitter @rikturr
 
Our Sponsor
Saturn Cloud is a data science and machine learning platform for scalable Python analytics. Users can jump into cloud-based Jupyter and Dask to scale Python for big data using the libraries they know and love, while leveraging Docker and Kubernetes so that work is reproducible, shareable, and ready for production.
Try Saturn Cloud for free at https://saturncloud.io 
Twitter: @saturn_cloud