Datascience

Encoders, cross attention and masking for LLMs: SuperDataScience Founder Kirill Eremenko returns to the SuperDataScience podcast, where he speaks with Jon Krohn about transformer architectures and why they are a new frontier for generative AI. If you’re interested in applying LLMs to your business portfolio, you’ll want to pay close attention to this episode!

This episode is brought to you by Ready Tensor, where innovation meets reproducibility (https://www.readytensor.ai/), by Oracle NetSuite business software (netsuite.com/superdata), and by Intel and HPE Ezmeral Software Solutions (http://hpe.com/ezmeral/chatbots). Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• How decoder-only transformers work [15:51]
• How cross-attention works in transformers [41:05]
• How encoders and decoders work together (an example) [52:46]
• How encoder-only architectures excel at understanding natural language [1:20:34]
• The importance of masking during self-attention [1:27:08]

Additional materials: www.superdatascience.com/759

The Super Data Science Podcast: Machine Learning | AI | Success

759: Full Encoder-Decoder Transformers Fully Explained, with Kirill Eremenko

Kirill Eremenko joins Jon Krohn for another exclusive, in-depth teaser for a new course just released on the SuperDataScience platform, “Machine Learning Level 2”. Kirill walks listeners through why decision trees and random forests are fruitful for businesses, and he offers hands-on walkthroughs for the three leading gradient-boosting algorithms today: XGBoost, LightGBM, and CatBoost.

This episode is brought to you by Ready Tensor, where innovation meets reproducibility (https://www.readytensor.ai/), and by Data Universe, the out-of-this-world data conference (https://datauniverse2024.com). Interested in sponsoring a SuperDataScience Podcast episode? Email natalie@superdatascience.com for sponsorship information.

In this episode you will learn:
• All about decision trees [09:17]
• All about ensemble models [21:43]
• All about AdaBoost [36:47]
• All about gradient boosting [45:52]
• Gradient boosting for classification problems [59:54]
• Advantages of XGBoost [1:03:51]
• LightGBM [1:17:06]
• CatBoost [1:32:07]

Additional materials: www.superdatascience.com/771

771: Gradient Boosting: XGBoost, LightGBM and CatBoost, with Kirill Eremenko

In this episode of the SuperDataScience Podcast, I chat with the Machine Learning Research Scientist, John Langford. You will hear about unsupervised, supervised learning and reinforcement learning, and the differences between the three. You will learn about applications of contextual bandits and reinforcement learning in general, YOLO style algorithms versus simulator algorithms, technics for avoiding local optimums. You will also learn about the balance between exploration and exploitation, learning to search and active learning.

If you enjoyed this episode, check out show notes, resources, and more at www.superdatascience.com/275

The Super Data Science Podcast: Big Data | Analytics Careers | Mentors | Success

SDS 275: Machine Learning Through Reinforcement & Contextual Bandits

Today, we’re diving into our fifth and final part of our history of data science series by looking into data science’s future through the eyes of five of the most influential people in our space and how they see the next few decades.

Additional materials: www.superdatascience.com/352

SDS 352: History of Data Science - Part 5

Today, I’m talking about an interesting topic I found in our own Data Science newsletter about the need for hybrid AI models in the future.

Additional materials: www.superdatascience.com/362

Datascience

PDZ