L2ashobby

Reading: Data Analysis Using Regression and Multilevel/Hierarchical Models TIL: Since estimated regression coefficients are linear combinations of iid response variables, then by CLT, those coefficients estimated across different samples from the population will also be normally distributed.

Reading: Data Analysis Using Regression and Multilevel/Hierarchical Models TIL: "Fixed effects" models are just a special case of "random effects" models that assume zero or infinite higher level variance in parameters. So "all models are random effects models." (semantics!)

LoRA involves freezing all LLM layers and adding trainable low-rank weight matrices (AB) to specific layers to adjust their outputs and fine-tuning overall model predictions. This amounts to the low-rank matrices approximating the full weight updates that would have occurred during fine-tuning.

TIL: k-Means clustering is a special case of the Expectation-Maximization (EM) algorithm using Gaussian mixture models (GMM). If the K Gaussian clusters are assumed to have zero variance and uniform mixture coefficients (1/K), then the GMM algorithm becomes the k-means clustering algorithm.

TIL: While cross-entropy loss can be thought of as a comparison between two probability distributions, in ML coding practice, the loss function takes in a neural network's predicted logits and target probabilities. This way, loss computations are more efficient, with bounded stable gradients.

TIL: In k-means clustering, data samples are first assigned to clusters based on the squared distances to each cluster center. The algorithm then updates cluster centers by finding the centroid of the assigned data samples. Essentially, the cluster centers "follow" the newly assigned data samples.

TIL: "Bootstrap Aggregating" = Bagging. Commonly used for decision trees, it is also possible to use for training ensembles of other kinds of prediction functions with relatively high variance, including neural nets!

Reading: en.wikipedia.org/wiki/Feedfor... TIL: MLP is but one kind of feedforward network, specifically the kind with fully connected layers. Other kinds of feedforward network include CNNs.

Reading: OpenAI Spinning Up Part 3 TIL: The policy gradient used to update policy takes the general form of an expected weighted sum over the trajectory. The main summation term is the gradient of log-likelihood of policy actions. The summation weights depend on the policy optimization approach.

Reading: RL materials (David Silver RL slides, Spinning Up) TIL: In on-policy, the action for updating target policy becomes the next action (target = behavior policy). In off-policy, the action for updating target policy is not necessarily the next action (sampled from separate behavior policy).

Reading: Build a Large Language Model from Scratch, Chapter 3 TIL: Attention mechanisms were initially developed to augment the RNN EncDec architecture by addressing the limitation of how the original RNN Decoder could not access the RNN Encoder's previous hidden states over the input sequence.

Reading: Build a Large Language Model from Scratch, Chapter 2 TIL: While the OG transformer model used a pre-defined positional encoder that remained fixed during training, early OpenAI GPT models used absolute positional embeddings that were optimized during training.

Reading: Build a Large Language Model from Scratch, Chapter 2 TIL: Raw text is first processed into words and special character tokens. Then a tokenizer uses a vocabulary to map tokens to integer IDs and vice versa. Special context tokens (`endoftext`) are included in the vocabulary.

Reading: Build a Large Language Model from Scratch, Chapter 1 TIL: "when we say language models "understand," we mean that they can process and generate text in ways that appear coherent and contextually relevant, not that they possess human-like consciousness or comprehension."

Reading: FastAI Book github.com/fastai/fastb... Section: 04_mnist_basics TIL: In classification, using accuracy as a loss function is not a good idea because it likely does not change after model weight updates, resulting in zero gradient and "no learning."

Reading: FastAI Book github.com/fastai/fastb... Section: 04_mnist_basics TIL: "Gradient" in ML usually refers to the **computed value** of the function's derivative given input values, rather than the function's derivative expression per math/physics convention.

Reading: FastAI Book github.com/fastai/fastb... Section: 04_mnist_basics TIL: Arthur Samuel describes machine learning as "a mechanism for altering the weight assignment so as to maximize the performance." Kinda cool it doesn't rely on very formal math language.

Reading: Reality Check Slide Deck bsky.app/profile/kyun... TIL: Best practices to consider for evaluating models: 1) test with unseen tasks rather than data instances (continual learning), 2) use metrics informed by domain, not just ML, 3) test on tasks downstream from basic predictions (esp LLMs).

Reading: FastAI Book github.com/fastai/fastb... Section: 01_intro.ipynb TIL: "Computers, as any programmer will tell you, are giant morons, not giant brains." - Arthur Samuel, "Artificial Intelligence: A Frontier of Automation" doi.org/10.1177/0002...

Reading: Deep Learning [https://www.deeplearningbook.org] Section: Chapter 3 - Probability and Information Theory TIL: While KL-Divergence is sometimes referred to as a "distance" between distributions P and Q, this is not the best mental model since KL-divergence is asymmetric.

Reading: Deep Learning [https://www.deeplearningbook.org] Section: Chapter 3 - Probability and Information Theory TIL: In mixture distribution models, the component identity variable c is a kind of latent variable!

Reading: Deep Learning [https://www.deeplearningbook.org] Section: Chapter 3 - Probability and Information Theory TIL: Covariance measures a *linear* relationship between two variables. So Cov(x,y)=0 does not exclude the possibility of a non-linear relationship between x and y.

hello world!