Data Science at Home

Embedded Machine Learning: Part 4 - Machine Learning Compilers (Ep. 185)

In this episode I speak about machine learning compilers, the most important tools to bridge the gap between high level frontends, ML backends and hardware target architectures.
There are several compilers one can choose. Before that, let's get familiar with what a compiler is supposed to do.
Enjoy the episode!
 
Chat with me
Join us on Discord community chat to discuss the show, suggest new episodes and chat with other listeners!
 
Sponsored by Amethix Technologies
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.
 
Links
Amethix Embedded Machine Learning
https://tvm.apache.org/
https://github.com/pytorch/glow
https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html
 
 
 
 

Embedded Machine Learning: Part 3 - Network Quantization (Ep. 184)

In this episode I speak about neural network quantization, a technique that makes networks feasible for embedded systems and small devices.
There are many quantization techniques depending on several factors that are all important to consider during design and implementation.
Enjoy the episode!
 
Chat with me
Join us on Discord community chat to discuss the show, suggest new episodes and chat with other listeners!
 
Sponsored by Amethix Technologies
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.
 
Links
Amethix Embedded Machine Learning
Introduction to quantization on Pytorch
 
 
 

Embedded Machine Learning: Part 2 (Ep. 183)

In Part 2 of Embedded Machine Learning, I speak about one important technique to prune a neural network and perform inference on small devices. Such technique helps preserving most of the accuracy with a model orders of magnitude smaller.
Enjoy the show!
 
 
References
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
 

Embedded Machine Learning: Part 1 (Ep.182)

This episode is the first of a series about Embedded Machine Learning. I explain the requirements of tiny devices and how it is possible to run machine learning models.
 
Join us on Discord community chat to discuss the show, suggest new episodes and chat with other listeners!
 
Sponsored by Amethix Technologies
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.
 
 
References
https://datascienceathome.com/compressing-deep-learning-models-distillation-ep-104/
 

History of Data Science (Ep. 181)

How did we get here? Who invented the methods data scientists use every day?
We answer such questions and much more in this wonderful episode with Triveni Gandhi, Senior Data Scientist and Shaun McGirr, AI Evangelist at Dataiku. We cover topics about the history of data science, ethical AI and...
 
This episode is brought to you by Dataiku
With Dataiku, you have everything you need to build and deploy AI projects in one place, including easy-to-use data preparation and pipelines, AutoML, and advanced automation.
 
and by Amethix Technologies
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.
 
References
www.historyofdatascience.com
 

Capturing Data at the Edge (Ep. 180)

In this episode I speak with Manavalan Krishnan from Tsecond about capturing massive amounts of data at the edge with security and reliability in mind.
 
This episode is brought to you by Tsecond
The growth of data being created at static and moving edges across industries such as air travel, ocean and space exploration, shipping and freight, oil and gas, media, and more proposes numerous challenges in capturing, processing, and analyzing large amounts of data.
and by Amethix Technologies
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.
 
References
https://tsecond.us/company/manavalan-krishnan/
 

[RB] Composable Artificial Intelligence (Ep. 179)

If you think deep learning is a method to get to AGI, think again. Humans, as well as all mammals think in a... composable way.
Come chat with us on Discord
 
Sponsors
This episode is brought to you by Amethix Technologies
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.
 

What is a data mesh and why it is relevant (Ep. 178)

Sponsors
This episode is brought to you by Amethix Technologies
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.
 
Join us on Discord
Feel free to drop by and have a chat with the host and the followers of the show
 
 

Environmentally friendly AI (Ep. 177)

Sponsors
This episode is brought to you by Advanced RISC Machines (ARM). ARM is a family of reduced instruction set computing architectures for computer processors https://www.arm.com/
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.

Do you fear of AI? Why? (Ep. 176)

This episode summarizes a study about trends of AI in 2021, the way AI is perceived by people of different background and some other weird questions.
For instance, would you have sexual intercourse with a robot? Would you be in a relationship with an artificial intelligence?
The study has been conducted by Tidio.com and reported at https://www.tidio.com/blog/ai-trends/
 
 
Sponsors
This episode is supported by Amethix Technologies.Amethix uses machine learning and advanced analytics to empower people and organizations to ask and answer complex questions like never before.Coming soon at https://amethix.com