Index
Recently, I've started using org-roam to take notes in the Zettelkasten style. I've found these notes to be helpful both in reviewing old material and keeping track of new information.
In my reading, whenever I come across a concept that I haven't seen or don't remember well, I make a new note. These notes aren't organized into categories or hierarchies, but connections between notes exist as links and back-links.
- functors (haskell)
- applicative functors (haskell)
- Types in Haskell
- Device File
- Partition
- File Systems
- inode
- Mount
- Virtual File System
- System Call
- Installing a new drive
- Unified Extensible Firmware Interface
- Boot Process
- Dynamic Host Configuration Protocol
- Network Managers on Arch
- Arch post-install
- Linux Backup
- Devlin et al 2018 - BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
- Vaswani et al 2017 - Attention Is All You Need
- Attention
- Transformer
- Lu et al 2019 - ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks
- Carion et al 2020 - End-to-End Object Detection with Transformers
- Residual blocks
- layer normalization
- Kinds in Haskell
- Typeclasses in Haskell
- Currying in Haskell
- Feature Pyramid Networks for Object Detection
- Convolutional Networks
- Ren et al 2015 - Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- Region of Interest Pooling
- Assignment Problem
- Erler 2010 - Does Memory Modification Threaten Our Authenticity?
- Memory
- Rejection Sampling
- Inverse transform sampling
- probability integral transform
- Blogs
- Pointers in C
- Machine Code
- Registers
- Assembly Language
- Compilers
- Compiler Example: C to Assembly
- Modern Compilers
- How compilers handle procedure calls
- Baye's Rule
- Entropy
- Decision Trees
- Kullback-Leibler divergence
- Gini impurity
- Convergence Almost Surely
- Convergence in Probability
- Publish org notes to HTML
- Information Content
- Jensen's Inequality
- Law of the unconscious statistician
- lazy evaluation
- Combinators
- Y Combinator
- Maximum Likelihood Estimation
- Joint Entropy
- Kraft-McMillan Inequality
- softmax
- Cross Entropy
- sigmoid
- Hierarchical Softmax
- Mikolav et al 2013 - Distributed Representations of Words and Phrases and their Compositionality
- CYK Algorithm
- Law of Large Numbers
- Bayesian Inference
- Frequentist vs Bayesian Inference
- Policy Gradient
- Markov's Inequality
- Semantic Parsing
- Dunietz et al 2020 - To Test Machine Comprehension, Start by Defining Comprehension
- Peters et al 2018 - Deep contextualized word representations
- Tenney et al 2019 - BERT Rediscovers the Classical NLP Pipeline
- Ramsey Number
- Pascal's Rule
- Synecdoche vs Metonymy
- Cross Validation
- Firth 1957 - A Synopsis of Linguistic Theory
- TF-IDF
- Turney and Pantel 2010 - From frequency to meaning: Vector space models of semantics
- Precision vs Recall
- Reduction
- Model Theory
- Semantic Theory of Truth (Tarski)
- Frege's theory of sense and denotation
- Intuitionistic Type Theory
- Sampling
- greatest common denominator
- (markov chains) aperiodicity
- Metropolis-Hastings
- Markov Chain Monte Carlo
- Monads
- Importance Sampling
- Linker
- LSTM
- Scalar Implicature
- Grice's Maxims
- Goodman and Frank 2016 - Pragmatic Language Interpretationas Probabilistic Inference
- Referential Transparency
- Git rebase vs merge
- Git reset vs checkout
- Expectation Maximization
- Zero configuration networking
- Arch printing
- ssh
- grad school advice
- git submodule
- reinforcement learning
- multi-armed bandit problem
- Actor Critic
- Papadimitriou et al 2020 - Brain computation by assemblies of neurons
- Conferences and Journals
- research reading list
- Hu and Singh 2021 - Transformer is All You Need: Multimodal Multitask Learning with a Unified Transformer
- Merrill 2021 – Formal Language Theory Meets Modern NLP
- hammersley-clifford theorem
- https
- Prasanna 2020 – When BERT Plays The Lottery, All Tickets Are Winning
- Marasović 2018 – NLP’s generalization problem, and how researchers are tackling it
- Conneau and Lample 2018 – Word Translation without Parallel Data
- Ruder 2019 – The 4 Biggest Open Problems in NLP
- mutual information
- source coding theorem
- noisy channel coding theorem
- gumbel distribution
- gumbel max trick
- reparameterization trick
- gumbel softmax
- spearman's rank correlation coefficient
- pearson correlation coefficient
- conditional entropy
- Convergence in Distribution
- central limit theorem
- satisfiability modulo theories
- Chernoff bound
- change of basis
- conditional dependence
- rent seeking
- lagrange multipliers
- Qin and Eisner 2021 – Learning How to Ask: Querying LMs with Mixtures of Soft Prompts
- policy iteration
- Antoniak and Mimno 2021 – Bad Seeds: Evaluating Lexical Methods for Bias Measurement
- value iteration
- off-policy policy gradient
- Trust Region Policy Optimization
- Proximal Policy Optimization
- Dai and Yang 2019 – Transformer-XL: Attentive language models beyond a fixed-length context
- Gaussian Processes
- perplexity
- multiple dispatch
- Dehghani et al 2021 – The Benchmark Lottery
- sufficient statistic
- Bellman equation
- Mnih et al 2013 – Playing Atari with Deep Reinforcement Learning (Deep Q-Learning)
- probability space
- Measures and Probability Measures
- Sigma Field
- Caratheodory's Extension Theorem
- Lebesgue Measure
- ex ≥ 1 + x
- independence
- conditional probability
- law of total expectation
- iterated expectation
- random variable
- cumulative distribution function
- Neyman-Pearson Lemma
- bayesian hypothesis test
- group (algebra)
- receiver operating characteristic
- hypothesis testing
- lambda calculus
- hoeffding's inequality
- polynomial interpolation
- rank nullity theorem
- phantom type
- properties of expectation
- covariance
- simpson's paradox
- bayesian network
- lebesgue integral
- Big Step Semantics
- Kim 2021 – Sequence-to-Sequence Learning with Latent Neural Grammars
- convergence in mean
- confidence interval
- one tailed hypothesis test
- parser combinator
- convergence of random variables
- bootstrapping (statistics)
- ELisp
- Bommasani et al 2021 – On the Opportunities and Risks of Foundation Models
- parametric vs non-parametric models
- assorted terms from linguistics
- Index