data-umbrella / event-transcripts Goto Github PK

Event: R, an Ecosystem Where Pythonistas Can Thrive

## Upcoming Events
Join our Meetup group for more events!
https://www.meetup.com/data-umbrella

## Agenda
00:00:00 to 00:05:50 Introduction to Data Umbrella 
00:05:50 Ian Introduction
00:56:30 Q&A begins
01:08:30 Demo of RStudio IDE
 
## Event
This talk will introduce Python users to the R ecosystem. Attendees should expect that by the end of the talk they will understand how to get started with reporting infrastructure in Python and R; and how to use open standards to share data across data products. As part of the discussion, we will see different use cases for both languages, their integration, and common pitfalls.

## Speaker
Ian is a data person with a background in Data Science and DevOps. He has experience consulting within the pharmaceutical industry, government sector, NGOs and educational institutions in multiple countries. As part of his academic background he holds a Master’s degree in Data Science from the University of British Columbia. Outside of work, he is a certified freediver, loves to surf in the Northeast coast of Puerto Rico and cooks spicy food.

## Slides:  
https://ian-flores.github.io/r-ecosystem-4-python-slides/slides.html#1

## Resources
https://github.com/ian-flores/r-ecosystem-4-python

Pablo Duboue: Solving NLP (Natural Language Processing) Tasks Using LLMs (Large Language Models) 

## Timestamps 
00:00 Data Umbrella Introduction
02:43 Speaker Introduction + Land Acknowledgment
04:52 Agenda
06:15 NLP history (rule-based, statistical, deep learning)
09:00 What is a Language Model?
10:35 Large Language Models
11:55 Training LLMs - more than just language
12:48 Speaker background
13:35 About this talk - more background
14:26 Section 1: NLP / LLM Tasks - Part-of-Speech tagging
15:48 POS tagging example
16:50 NLP Tasks - Named Entity Recognition (NER), example
17:50 NLP Tasks - Information Extraction (IE), example
19:08 NLP Tasks - Sentiment Analysis, example
20:32 Q&A - data tagging
22:41 Section 2: Prompting 101
22:51: OpenAI API - intro, CLI, Python
25:44 Zero shot - no examples, temperature, output/hallucinations
28:35 Few shot - training data, output, GPT-4
30:17 Handling priors in exemplars
30:40 Chain-of-thought (CoT)
31:13 LLM role
31:43 Recursing
32:23 Learning more - additional resources
33:14 Section 3: Solving NLP Tasks with OpenAI API
33:27 OpenAI POS tagging
34:11 Output is unstable
34:21 Better prompt
34:40 Annotation Manual
36:03 NER prompt, unstable output, MUC-6 locations
38:28 ChatGPT output
38:41 GPT4 output
39:00 Q&A - AGI
40:28 IE prompt - relation extraction, stable output
42:31 Sentiment Analysis prompt
43:26 Additional discourse
44:22 Section 4: Using open source LLMs
44:39 Why open source LLMs
45:44 Issues with open source models
46:33 Examples of open source LLMs
49:29 Conclusions
51:34 Q&A - contributing to new models v. expanding on older ones, LLMs in cell phones, communication changes and abstraction, etc.

## Resources
- https://tellandshow.org/ (community-owned machine learning)
- http://textualization.com/gptwhitepaper/ 
- http://artoffeatureengineering.com/ 
- http://wiki.duboue.net/A_Dollar_Worth_Of_Ideas (project ideas)

## Connecting
- LinkedIn: https://www.linkedin.com/in/pabloduboue/
- GitHub: https://github.com/drdub 
- Twitter: @pabloduboue

00:00 Introduction
10:00 example
12:23 example

Added timestamps for [topic x]

Towards #92
Closes #xxx [replace xxx with related issue, if there is one]

Shivay Lamba: Machine Learning in JavaScript: An Introduction to TensorFlowJS

## Timestamps 
00:00 Data Umbrella Introduction
03:06 Speaker Introduction
04:17 Presentation Intro - Machine Learning for the Web: Introduction to TensorFlow.JS
06:27 Why do we need machine learning in JavaScript (JS)?
08:02 What is TensorFlow?
09:03 Versatility & language popularity - ML can be used on any platform JS can run
10:30 ML application ideas (e.g. accessible web apps, sound recognition, etc.) 
11:38 3 options for using TensorFlow
13:00 Option 1: Use pre-trained models with JS classes 
15:14 Real-world examples
19:15 Option 2: Retrain existing neural network models to work with your own data
19:51 Image classification example (100 images) with Teachable Machine (separate tool with downloadable code)
26:24 Pause for Q&A
26:55 Example using Cloud Auto ML for larger image datasets (100,000+)
28:29 Option 3: Coding your own model
29:32 High-level TensorFlow architecture
31:06 Backends and hardware execution
32:07 Chart - Model Inference Performance Only
32:45 Chart - performance comparison between JS and Python of Hugging Face DistilBERT (NLP-based model)
33:05 5 benefits of using TensorFlow on the front end (client side) 
33:59 4 benefits of using TensorFlow on the back end (server side)
35:00 Demo code example 1 - image detection
42:35 Demo code example 2 - TensorFlow.JS converter (converting Python model to JS model)
47:24 More resources for learning and inspiration
49:40 Join the community - #MadeWithTFJS 
50:34 What will you make? Machine learning is for everyone.
50:57 Q&A (Using PyTorch, using TensorFlow in production) & final thoughts


## Resources
Website / API: https://www.tensorflow.org/js 
Models: https://www.tensorflow.org/js/models 
GitHub Code: https://github.com/tensorflow/tfjs 
Google Group: [[email protected]](mailto:[email protected]) 
TensorFlow forum: https://discuss.tensorflow.org/tag/tjfs 
YouTube playlist: goo.gle/made-with-tfjs 
Codepen: https://codepen.io/topic/tensorflow/ 
Glitch: https://glitch.com/@TensorFlowJS 
Sample dataset: https://www.kaggle.com/datasets/uciml/pima-indians-diabetes-database 
Recommended Reading: Deep Learning with JavaScript - https://www.manning.com/books/deep-learning-with-javascript 
Book: LearningTensorFlow.js - https://github.com/GantMan/learn-tfjs 
edX: https://www.edx.org/learn/javascript/google-google-ai-for-javascript-developers-with-tensorflow-js