Sketching the Journey of Learning

Bali's notes & demos.

Sketching the Journey of Learning | Bali’s notes & demos.

Notes for Prof. Hung-Yi Lee's ML Lecture: Normalization

Normalization and Error Surface

Notes for Prof. Hung-Yi Lee's ML Lecture: Transformer

Overview

Notes for Prof. Hung-Yi Lee's ML Lecture: Self-Attention

Self-Attention

Exception Handling

The program tries to execute the code in the try clause first. If an exception is raised and the exception match the type of an except clause, the progem execute the code in that except clause. If no exception is raised in the try clause, the program then execute the code in the else clause. The program execute the code in the finally clause after all the try, except, else clauses wheter or not the try statement produces and exception.

Thread vs Process

A thread is an execution context, which is all the information a CPU needs to execute a stream of instructions. A process is a bunch of resources associated with a computation, or an executing instance of a program. A process can have one or many threads. Resources are allocated to the processes, and resoueces of different process are not shared with others. To share resources between proecesses, one have to do special handling, e.g. using pipes of queue to share information. All the threads of a process share all its resoureces, e.g. memory.

The Curse of Dimensionality

The curse of dimensionality refers to various phenomena that arise when analyzing and organizing data in high-dimensional spaces that do not occur in low-dimensional settings. The common theme of these problems is that when the dimensionality increases, the volume of the space increases so fast that the available data become sparse. In order to obtain a reliable result, the amount of data needed often grows exponentially with the dimensionality. Also, organizing and searching data often relies on detecting areas where objects form groups with similar properties; in high dimensional data, however, all objects appear to be sparse and dissimilar in many ways, which prevents common data organization strategies from being efficient.

Chap 3: Capital Share Bikeshare Predictor

Follow the book’s approach screenshot version

Chap 3: Capital Share Bikeshare Predictor: Follow the Book

Import

Notes for Prof. Hung-Yi Lee's ML Lecture: Reinforcement Learning

Overview of Reinforcement Learning

Notes for Prof. Hung-Yi Lee's ML Lecture: Ensemble

Ensemble: Bagging