wataru

A coffee lover, a biker, a jogger, a weekend wanderer, and a part-time statistician. これは公式に非公式なアカウントです。表現は選ぶよう努めていますが、良からぬ発言は怒らず晒さずご指摘ください…。また、フォローよりリスト、派です。

[Piyo@個人開発してるリーマン @shizuku837335]

すごい…
ラプラス変換でも反応がよい…

レベルを上げてこれならどうですか…？！
(もはや分かる方が分かれば良い)
#留数定理 #逆ラプラス変換 #エンジニア #理系

[徐伦 @Jolyne_AI]

想系统学数学，教材、视频、题库遍地都是；真正靠谱的优质资源却零散难寻，光筛选就能耗掉大把时间。

我在 GitHub 上挖到一份很省心的清单：Awesome Math——把高质量数学资源按学科体系整理好的一站式索引，已拿下 14k+ stars。

它覆盖代数、几何、分析、概率统计、数论等 30+ 领域，把入口统一收拢；形式也齐全：视频课、电子教材、练习工具都有，甚至还能找到 MIT、哈佛等名校学生的课程笔记。

GitHub：https://t.co/vEo6jaNILw

资源经过筛选并持续更新；如果你打算自学数学，这份清单值得直接收藏。

[SKG @sonukg4india]

The figure of mathematics

[Ashutosh Maheshwari @asmah2107]

Inference optimizations I’d study if I wanted sub-second LLM responses:

Bookmark this.

1.KV-Caching
2.Speculative Decoding
3.FlashAttention
4.PagedAttention
5.Batch Inference
6.Early Exit Decoding
7.Parallel Decoding
8.Mixed Precision Inference
9.Quantized Kernels
10.Tensor Parallelism
11.Pipeline Parallelism
12.Sequence Parallelism
13.Graph Optimization (ONNX, TensorRT)
14.Dynamic Batching
15.Memory Offloading
16.Streaming Generation

[Frank Nielsen @FrnkNlsn]

Book #OTD

"Learning Theory:
An Approximation Theory Viewpoint"

[Quant Science @quantscience_]

Machine learning techniques and data for stock market forecasting.

(A free 41-page PDF) 👇

[Rohit Kumar Tiwari @_rohit_tiwari_]

PyTorch Fundamentals: Your First Steps into Hands-on Deep Learning.

Github (900+ stars): https://t.co/pFon17yIOk
Introduction to PyTorch fundamentals, covering tensor initialization, operations, indexing, and reshaping.

[Mustafa @oprydai]

study physics with math.

otherwise you’re just collecting metaphors.

• force → vectors, not vibes
• motion → calculus, not intuition
• energy → equations, not slogans
• fields → geometry, not magic
• waves → functions moving through space

physics tells you what reality does.

math tells you why it does it.

separate them and you get shallow understanding.

combine them and the world starts exposing its source code.

[Dhanian 🗯️ @e_opore]

DSA (Data Structures & Algorithms) Complete Roadmap
|
| | |-- Fundamentals
| |-- Programming Basics
| | |-- Variables and data types
| | |-- Loops and conditions
| | |-- Functions and recursion
| |-- Complexity Analysis
| | |-- Big O notation
| | |-- Time complexity
| | |-- Space complexity
| |-- Problem Solving Basics
| | |-- Pattern recognition
| | |-- Dry runs
| | |-- Edge cases

| | |-- Arrays & Strings
| |-- Array operations
| |-- Prefix and suffix sums
| |-- Sliding window
| |-- Two pointers
| |-- String manipulation
| |-- Hashing basics

| | |-- Linked Lists
| |-- Singly linked list
| |-- Doubly linked list
| |-- Circular linked list
| |-- Fast & slow pointers
| |-- Reversing linked lists

| | |-- Stacks & Queues
| |-- Stack implementation
| |-- Queue implementation
| |-- Monotonic stack
| |-- Priority queue (Heap)
| |-- Deque

| | |-- Trees
| |-- Binary Trees
| |-- Binary Search Trees
| |-- Tree Traversals
| | |-- DFS
| | |-- BFS
| |-- AVL Trees
| |-- Segment Trees
| |-- Fenwick Trees

| | |-- Graphs
| |-- Graph Representation
| |-- BFS & DFS
| |-- Topological Sorting
| |-- Shortest Path Algorithms
| | |-- Dijkstra
| | |-- Bellman-Ford
| | |-- Floyd-Warshall
| |-- Minimum Spanning Tree
| | |-- Prim's Algorithm
| | |-- Kruskal's Algorithm
| |-- Union Find (DSU)

| | |-- Searching & Sorting
| |-- Binary Search
| |-- Merge Sort
| |-- Quick Sort
| |-- Heap Sort
| |-- Counting Sort
| |-- Radix Sort

| | |-- Recursion & Backtracking
| |-- Recursive thinking
| |-- Backtracking patterns
| |-- N-Queens
| |-- Sudoku Solver
| |-- Permutations & combinations

| | |-- Dynamic Programming
| |-- Memoization
| |-- Tabulation
| |-- Knapsack problems
| |-- Longest Common Subsequence
| |-- Longest Increasing Subsequence
| |-- Matrix DP

| | |-- Greedy Algorithms
| |-- Activity selection
| |-- Huffman coding
| |-- Fractional knapsack
| |-- Interval scheduling

| | |-- Advanced Algorithms
| |-- Bit Manipulation
| |-- Trie
| |-- Suffix Array
| |-- KMP Algorithm
| |-- Rabin-Karp
| |-- Manacher's Algorithm

| | |-- Competitive Programming
| |-- Fast I/O
| |-- Modular arithmetic
| |-- Number theory basics
| |-- Combinatorics
| |-- Mathematical algorithms

| | |-- Interview Preparation
| |-- Coding interview patterns
| |-- Blind 75 problems
| |-- LeetCode Top 150
| |-- Mock interviews
| |-- Whiteboard problem solving

| | |-- Real World Projects
| |-- Build a spell checker using Trie
| |-- Route finder with Graph algorithms
| |-- Cache system using LRU Cache
| |-- Search engine indexing demo
| |-- Task scheduler with Priority Queue

| | |-- Community and Growth
| |-- Practice on LeetCode
| |-- Solve Codeforces problems
| |-- Participate in coding contests
| |-- Share solutions on GitHub
| |-- Contribute to open source

Grab Master Data Structures & Algorithms ebook:
https://t.co/Y2uMlOqQZl

[Swapna Kumar Panda @swapnakpanda]

MIT's Books on AI & ML (FREE DOWNLOAD):

1. Foundations of Machine Learning
https://t.co/78p57EBbL8

2. Understanding Deep Learning
https://t.co/D2oyRrXqcE

3. Introduction to Machine Learning Systems
❯ Vol 1: https://t.co/IezLFJdhDV
❯ Vol 2: https://t.co/NYP3xAPZ6u

4. Algorithms for ML
https://t.co/lntuD4Q19H

5. Deep Learning
https://t.co/vCHVIZQYTI

6. Reinforcement Learning
https://t.co/JNWhFCuCkH

7. Distributional Reinforcement Learning
https://t.co/GXpkV4BDZi

8. Multi Agent Reinforcement Learning
https://t.co/T8zVmQVutO

9. Agents in the Long Game of AI
https://t.co/HeD3Nsm5zz

10. Fairness and Machine Learning
https://t.co/csAjhdf7Lb

11. Probabilistic Machine Learning

❯ Part 1 : https://t.co/5Leef9ypGj
❯ Part 2 : https://t.co/vRbF0rEIuh

[Antonio Lupetti @antoniolupetti]

"Mathematics of Neural Networks" is an excellent set of lecture notes for anyone who wants to study modern neural networks from a mathematical perspective.

It covers supervised learning, artificial neurons and activation functions (ReLU, sigmoid, tanh, swish, softmax), shallow and deep neural networks, stochastic gradient descent, weight initialization, vanishing and exploding gradients, convolutional neural networks, automatic differentiation, backpropagation, adaptive optimization algorithms (Adagrad, RMSProp, Adam), and concludes with modern geometric concepts such as manifolds, Lie groups, equivariance, group convolutions, and rotation-translation equivariant CNNs.

I recommend keeping it in your bookmarks as a useful reference whenever you need to explore the mathematics behind neural networks.

https://t.co/78VDWxjDUa

[Dan Kornas @DanKornas]

Stop learning LLM internals from random one-off tutorials.

LLM Internals is a step-by-step GitHub learning repo for understanding how large language models work under the hood.

It helps you build a cleaner mental model by organizing blogs and videos from tokenization to attention math, Transformer components, training concepts, and inference optimization.

Key features:

• Fundamentals first – starts with LLMs, RAG, MCP, agents, fine-tuning, quantization, tokenization, and BPE
• Attention math – walks through Q/K/V, √dₖ scaling, causal masking, RoPE, and grouped-query attention
• Transformer components – covers the architecture, feed-forward networks, normalization, MoE, and LoRA
• Training concepts – includes backpropagation, cross-entropy loss, RLHF, and reasoning models
• Inference optimization – covers KV cache, paged attention, Flash Attention, speculative decoding, continuous batching, and prompt caching

It’s open-source (Apache License 2.0).

Link in the reply 👇

[academi study w @academiastudygd]

C++ · Physics · Calculus — Integrated Stem Bundle for CS students https://t.co/UB1za8qrob

[Kirk Borne @KirkDBorne]

Updated 2204-page PDF Mathematics ebook:

"Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning"

Find it here: https://t.co/HZc0LRoD7R

[wataru @wataruchan]

このところずっとGarmin提供のYour MasterというWatch Faceを使っていました。でもVenu 3以降には対応しなくなったようです。残念です。https://t.co/pJk2ddwkJj

[Dan Kornas @DanKornas]

Learn NLP and language modeling with a structured Stanford course.

What you will learn:
- Work with sequence, text, and language-modeling problems
- Understand how models learn, optimize, and improve from data
- Build a clearer mental model of code Generation
- Build a practical understanding of this part of NLP and language modeling

Link is in the first comment 👇

♻️ Share this with your network if you found it useful or insightful.

[Pratham @Prathkum]

Everyone is chasing self-improving models.

The bigger opportunity is self-improving products. Your users generate the best learning signal every single day.

I think that's where the real competitive advantage will come from.

[Kirk Borne @KirkDBorne]

Hey Data Scientists! You’re great data superheroes already. But go deeper with *top* Data Science books: https://t.co/gvorH6qvTT

PS. There’s this thing called PRIME DAY happening right now.

[Rohit Kumar Tiwari @_rohit_tiwari_]

Builds GPT-like LLMs from scratch in PyTorch

> Breaks the LLM architecture into simple parts.
> Beginner friendly.
> Fully hands on.

https://t.co/sbqfNxbBVC

> Everything explained step by step.
> Just 10 notebooks.

01_tokenization.ipynb
02_token_embeddings.ipynb
03_positional_embeddings.ipynb
04_self_attention_mechanism.ipynb
05_multi_head_self_attention.ipynb
06_feedforward_neural_networks.ipynb
07_residual_connections.ipynb
08_layer_normalization.ipynb
09_transformer_block.ipynb
10_mini_gpt.ipynb

[Quant Science @quantscience_]

There's a curve in finance that most investors get wrong.

It's called the efficient frontier.
Markowitz defined it in 1952.
Most investors still don't understand what it means in practice.

Here's what they get wrong: