AAAI2023「Are Transformers Effective for Time Series Forecasting?」と、HuggingFace「Yes, Transformers are Effective for Time Series Forecasting (+ Autoformer)」の紹介です。
本スライドは、弊社の梅本により弊社内の技術勉強会で使用されたものです。
近年注目を集めるアーキテクチャーである「Transformer」の解説スライドとなっております。
"Arithmer Seminar" is weekly held, where professionals from within and outside our company give lectures on their respective expertise.
The slides are made by the lecturer from outside our company, and shared here with his/her permission.
Arithmer株式会社は東京大学大学院数理科学研究科発の数学の会社です。私達は現代数学を応用して、様々な分野のソリューションに、新しい高度AIシステムを導入しています。AIをいかに上手に使って仕事を効率化するか、そして人々の役に立つ結果を生み出すのか、それを考えるのが私たちの仕事です。
Arithmer began at the University of Tokyo Graduate School of Mathematical Sciences. Today, our research of modern mathematics and AI systems has the capability of providing solutions when dealing with tough complex issues. At Arithmer we believe it is our job to realize the functions of AI through improving work efficiency and producing more useful results for society.
This document summarizes a research paper on scaling laws for neural language models. Some key findings of the paper include:
- Language model performance depends strongly on model scale and weakly on model shape. With enough compute and data, performance scales as a power law of parameters, compute, and data.
- Overfitting is universal, with penalties depending on the ratio of parameters to data.
- Large models have higher sample efficiency and can reach the same performance levels with less optimization steps and data points.
- The paper motivated subsequent work by OpenAI on applying scaling laws to other domains like computer vision and developing increasingly large language models like GPT-3.
NagoyaStat #12 で使用した資料です(公開に当たって当日ホワイトボードに書いた内容等を補完したものになります)。
「StanとRでベイズ統計モデリング」の第9章前半になります。
第9章のテーマは行列やベクトルを使った演算の高速化です。
---
The title of textbook is "Bayesian statistical modeling with Stan and R", and that of Chapter 9 in textbook is "advanced grammar" in English.
This document summarizes a research paper on scaling laws for neural language models. Some key findings of the paper include:
- Language model performance depends strongly on model scale and weakly on model shape. With enough compute and data, performance scales as a power law of parameters, compute, and data.
- Overfitting is universal, with penalties depending on the ratio of parameters to data.
- Large models have higher sample efficiency and can reach the same performance levels with less optimization steps and data points.
- The paper motivated subsequent work by OpenAI on applying scaling laws to other domains like computer vision and developing increasingly large language models like GPT-3.
NagoyaStat #12 で使用した資料です(公開に当たって当日ホワイトボードに書いた内容等を補完したものになります)。
「StanとRでベイズ統計モデリング」の第9章前半になります。
第9章のテーマは行列やベクトルを使った演算の高速化です。
---
The title of textbook is "Bayesian statistical modeling with Stan and R", and that of Chapter 9 in textbook is "advanced grammar" in English.
This document discusses the development of libkonn, a Haskell library for accessing Twitter's APIs. It uses Haskell and ByteString to process JSON from the Twitter stream and REST APIs. Multiple streamers can run concurrently to gather tweets and store them in MongoDB. The library includes a tweet extractor that analyzes tweet text and metadata to identify replies, retweets, and mentions. It also provides a demo web interface built with Snap and Heist that visualizes tweet relationships as a graph.
Template Haskell allows code to be generated at compile time by splicing quasi quotations into the abstract syntax tree. It works by running Haskell code that constructs syntax expressions and splicing the results into the code being compiled. This allows features like generating boilerplate code, domain-specific languages, and compile-time metaprogramming in Haskell.
IoT Devices Compliant with JC-STAR Using Linux as a Container OSTomohiro Saneyoshi
Security requirements for IoT devices are becoming more defined, as seen with the EU Cyber Resilience Act and Japan’s JC-STAR.
It's common for IoT devices to run Linux as their operating system. However, adopting general-purpose Linux distributions like Ubuntu or Debian, or Yocto-based Linux, presents certain difficulties. This article outlines those difficulties.
It also, it highlights the security benefits of using a Linux-based container OS and explains how to adopt it with JC-STAR, using the "Armadillo Base OS" as an example.
Feb.25.2025@JAWS-UG IoT
39. 例:クィックソート
一般的に Haskell の例として出される qsort
実はこれは偽物
pivot してない、in-place じゃない、遅い……
qsort :: [Int] → [Int]
qsort [] = []
qsort (a : as) =
qsort [x | x ← xs, x ≦ a] ++ [a]
++ qsort [y | y ← ys, y > a]
40. 例:クィックソート
破壊的変更による本物のクィックソート(抜粋)
(出典:Quicksort in Haskell)
qsort' l r =
if1 (r > l) $ do
i ← auto l
j ← auto (r+1)
let v = a[l] :: E m a
iLTj = i < (j :: E m i)
while iLTj $ do
while ((i += 1) < mub && a[i] < v)
skip
while (a[j -= 1] > v) skip
if1 iLTj $ a[i] =:= a[j]
a[l] =:= a[j]
qsort' l (j-1)
qsort' i r