Introduction to Mathematical Optimisation in Python
by @zluvsand @Medium Read more: https://
buff.ly/46ZquaB #DataScience #BigData #ArtificialIntelligence #MI cc: @pascal_bornet @yvesmulkers @kuriharan
RESEARCH
-
Introduction to Mathematical Optimisation in Python
By
–
-
Neural Operators Generalize Neural Networks Beyond Fixed Dimensions
By
–
The class of neural operators contain all neural networks. Neural networks fix resolution or dimension of input and outputs before learning the mapping, while in neural operators we do not have this restriction. In figure, you can see this difference: neural networks assumes
-
Neural operators accelerate simulations and design
By
–
Our @NatRevPhys perspective article on neural operators and their ability to accelerate simulations and design is now out. https://
rdcu.be/dD8BI @Nature 1. Neural operators learn mappings between functions, e.g. spatiotemporal processes and partial differential equations. -
Memory Allocation Strategy in LLM Training Implementation
By
–
You can look at the raw training implementation here: https://
github.com/karpathy/llm.c
/blob/master/train_gpt2.c
… You'll see that we allocate all the required memory a single time in the beginning in one large block of 1D memory. From there on during training, no memory gets created or destroyed, so we stay at -
Implementing Neural Network Layers with Memory Pointer Management
By
–
Once you have all the layers, you just string all it all together. Not gonna lie, this was quite tedious and masochistic to write because you have to make sure all the pointers and tensor offsets are correctly arranged. Left: we allocate a single 1D array of memory and then
-
Overcoming Research Blocks: Strategies for Problem Solving
By
–
a common shared experience of the research process seems to be "getting stuck" what am i supposed to do when i'm stuck on a problem? read papers? write unit tests? meditate, go for a walk? or should i just think harder? (please help)
-
Flan-2 Published in JMLR: Scaling Instruction Tuning
By
–
Flan-2 is published in JMLR https://
jmlr.org/papers/v25/23-
0870.html
…. I think it's a nice piece of history. The work scaled instruction tuning with respect to model size and finetuning tasks, which both improved performance. Our MMLU was 75%, SOTA when the paper came out in Oct 2022. Our -
Stanford Launches AI Student Affinity Groups for Interdisciplinary Research
By
–
Within the same month, we launched the @StanfordHAI Student Affinity Groups to create new opportunities for students to work across disciplines and explore ideas for AI that benefits humanity. #MondayMilestones 17/n https://
hai.stanford.edu/news/building-
next-generation-ai-scholars
… -
Stanford Launches Congressional AI Bootcamp for Lawmakers
By
–
August 2022: We launched the Congressional Bootcamp on AI for lawmakers to learn from leading scholars and think critically about regulating and governing emerging tech. #MondayMilestones 15/n https://
hai.stanford.edu/congressional-
boot-camp-ai
… -
Stanford HAI Startup Series Connects Founders with AI Scholars
By
–
September 2022: We introduced the HAI Startup Series for Stanford-affiliated founders to connect with AI scholars and build a community of entrepreneurs and mentors. #MondayMilestones 16/n