precompute.net  Blog   About 

Index

About Me
4archives
0 Lifestyle Creep
How Much Lifestyle Creep Can You Afford
AWS Certified Machine Learning Specialty
2 Data Engineering
3 Exploratory Data Analysis
4 Modeling
5 Implementation and Operations
Activation Functions
Athena
Batch
BlazingText
Comprehend
Course AWS Certified Machinea Learning Specialty
Data Distributions
Data Pipeline
Data Stores
Data Types
Database Migration Service (DMS)
DeepAR
Elastic MapReduce
Factorization Machine
Feature Engineering
Glue
High Level ML Services
Hyperparameter Tuning
IP Insights
Image Classification
K-Means
KNN
Kinesis
Latent Dirichlet Allocation
Neural Topic Model
Object Detection
Object2Vec
PCA
QuickSight
Random Cut Forest
Reinforcement Learning
Rekognition
S3
SageMaker
Sagemaker Groud Truth
Semantic Segmentation
Seq2Seq
Step Functions
Time Series
XGBoost
BASB
202203171851 Why Do We Need Digital Notes
PARA
202205011841 CODE
202205011857 Perspective
202205011858 12 Favorite Problems
202205011859 Capture
202205011900 Capture Toolkit
202205011901 Organize
202205011902 Distill
202205011903 Express
202205011904 Progressive Summarization
202205052039 The Creative Process
202205121949 Retrieval
BASB Overview
Tagging
Write of Passage
BigScience
BigScience Overview
Datasets
Arabic
Basque
Bengali
Catalan
Chinese
English
French
Hindi
Indonesian
Portuguese
Spanish
Urdu
Vietnamese
Goals
SubProjects
Deduplication report
SimHash deduplication
Suffix Array Substring deduplication
Write Up
Blog Pages
Digital Garden
Ideas
OSS Projects
Posts
MOC Reading List
Resources
AI
Career
Engineering
Misc
Productivity
Sources
Hypothesis
5. Text Generation
ACL 2022 Highlights
Becoming an Independent Researcher and getting published in ICLR with spotlight
Bootstrapping Labels via ___ Supervision & Human-In-The-Loop
Creating Confidence Intervals for Machine Learning Classifiers
DALL·E 2 Pre-Training Mitigations
From aardvark to woke: inside the Oxford English Dictionary
Moving Beyond Mimicry in Artificial Intelligence
Optimizing Transformers with Hugging Face Optimum
Papers with Code - Papers with Code Newsletter #18
Python behind the scenes #13: the GIL and its effects on Python multithreading
Simplifying BERT-based models to increase efficiency, capacity
Techniques for Training Large Neural Networks
The independent researcher
Just Keep Buying
Literature Notes
Courses
CS224n
Lecture 1 Overview
Lecture 10 Question Answering
Lecture 11 Convolutional Neural Networks for NLP
Lecture 12 – Subword Models
Lecture 13 Contextual Word Embeddings
Lecture 14 Transformers and Self-Attention
Lecture 15 Natural Language Generation
Lecture 16 Coreference Resolution
Lecture 17 Multitasking Learning
Lecture 18 Constituency Parsing and TreeRNNs
Lecture 2 Word Vectors and Word Senses
Lecture 20 – Future of NLP + Deep Learning
Lecture 3 Word Window Classification, Neural Nets, and Calculus
Lecture 4 Back-propagation and computation graphs
Lecture 5 Dependency Parsing
Lecture 6 Language Modeling
Lecture 7 Vanishing Gradients, Fancy RNNs
Lecture 8 Translation, Seq2Seq, Attention
Lecture 9 Practical Tips for Final Projects
Lecture BERT and Other Pre-trained Language Models
CS224N NLP with Deep Learning (Winter 2019)
How to Organize your Workflow to Maximize Productivity
Mastering Productivity: Create a Custom System that Works
Course Productivity Masterclass - Principles and Tools to Boost Your Productivity
Readings
AN IMAGE IS WORTH 16X16 WORDS: TRANSFORMERS FOR IMAGE RECOGNITION AT SCALE
Article Lessions from my PhD
Redefining SOTA
Article Reflections on my (Machine Learning) PhD Journey
Scikit-learn Pitfalls
Article Top 10 Open Source MLOps Tools
Digital Zettelkasten
Book How to Take Smart Notes
How to Write a Paper with ZettleKasten
Zettlekasten Principles
DIT: SELF-SUPERVISED PRE-TRAINING FOR DOCUMENT IMAGE TRANSFORMER
Gu et al_2021_UniDoc
Learning with Signatures
Paper A Practical Survey on Faster and Lighter Transformers
Paper CANINE Pre-training an Efficient Tokenization-Free Encoder for Language Representation
Paper Charformer Fast Character Transformers via Gradient-based Subword Tokenization
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language
Paper DeBERTa Decoding-enhanced BERT with disentangled attention
Paper Fastformer Additive Attention Can Be All You Need
Gradients without Backpropagation
Hidden Techinical Debt in Machine Learning Systems
Paper Language Models are Few-Shot Learners
LayoutReader Pre-training of Text and Layout for Reading Order Detection
Paper Muppet Massive Multi-task Representations with Pre-Finetuning
Paper Robust Open-Vocabulary Translation from Visual Text Representations
Paper Shortformer Better Language Modeling using Shorter Inputs
Paper Supervised Contrastive Learning for Pre-trained Language Model Fine-tuning
Paper Switch Transformers
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
UNIPELT: A Unified Framework for Parameter-Efficient Language Model Tuning
Post Embedding Layer might not be Necessary for Your Next NLP Project
Log in Python
Deduplication in Modern Large-scale LM Datasets
Research Two-sample Hypothesis Testing
Spelling Correction with Denoising Transformer
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark
UniDoc Unified Pretraining Framework for Document Understanding
Unified Pretraining Framework for Document Understanding
Video Transformer in Transformer
Machine Learning Concepts
202204280830 Bayes Error
202204280834 Bootstrapping
Permanent Notes
202109261532 Machine Learning Optimization
202109261533 Adaptive Computation
202109261813 Randomness in Scikit-learn
202109261818 Mixture of Experts
202109281804 Data-centric AI
202110031750 Contrastive Learning
202110031800 Calibration in Machine Learning
202110091321 Open Vocabulary
202112251111 PyTorch Tricks
202112251133 Incorrect Data Labels
202112251244 Deep Work
202202081923 Workplace Productivity
202205112015 Effective Note-taking
202205202159 2x Rule
202205202200 Diminishing Marginal Utility
202205231928 Cost Equivalent Curve
202205231931 Transfer Learning Approaches
202205241111 Code Review Pyramid
202205241112 Deep Learning First Principles for Efficiency
202205241113 Hotelling's Two-sample T-squared Test
202205241114 How to Remember Names
202205241115 How to Work Hard
202205241116 Kernel Two-sample Test
202205281322 Four Things That Make Things Memorable
Privacy AI
01 Intro
03 Information Flow within Communities
System Design
Rate Limiter
Estimation
Interview
Scaling
aaa
blog
2021
05-May
QMK Keymap
QMK Keymaps
coffee
Beans
1850
1850 Midnight Gold
Brûlerie Rousseau
Espresso Italien
Café Sobab
Yirgacheffe
Les Bruleries
Brazil Cerrado
Equipment
Aeropress
Inverted Method
Comandante
Kettle
Moka Pot
Thermometer
Events
Descent
Fault
Improv
Factors
Brew Time
Grind Size
Water Temperature
Journal
2021
08
2021-08-29
2021-08-30
09
2021-09-07
2021-09-09
2021-09-11
2021-09-12
2021-09-13
2021-09-15
2021-09-16
2021-09-18
2021-09-19
2021-09-21
2021-09-23
2021-09-24
2021-09-29
10
2021-10-03
2021-10-04
2021-10-06
2021-10-31
Satisfaction
Excellent
Good
Meh
Nah
Science
Sensations
Aroma
Gustatory Notes
Dark Chocolate
Italian
Lemony
Shops
IGA
Provigo
Testfile