Lisa's notes: musings on daily life, work, study, personal growth, and casual reflections.
This article explains Java's 16‑bit char type, how Unicode literals are written, the role of the Character wrapper class, boxing and unboxing mechanics, immutability, common static methods, and proper use of escape sequences such as Unicode and quoted strings, with concrete code examples.
This tutorial walks through Java's core numeric and character utilities, covering number wrapper classes and autoboxing/unboxing, the Number hierarchy, formatted output with printf/format, DecimalFormat patterns, and the Math class’s constants and methods for arithmetic, logarithmic, trigonometric, and random number generation, all illustrated with concrete code examples.
This article explains the evolution of natural language processing, introduces transformer‑based large models such as BERT, GPT and T5, and details how words are represented through one‑hot vectors and dense word embeddings, illustrating their training and analogy capabilities.
The article explains how the Java final keyword can be applied to classes and methods to prevent inheritance and overriding, provides syntax and concrete code examples—including a final class and a final method in a chess algorithm—and advises using final for safety in constructors.
From the 1943 perceptron concept to modern Transformer-based large language models, this article traces the evolution of neural network techniques in NLP, highlighting key milestones such as early perceptrons, the 1986 back‑propagation breakthrough, statistical methods, LSTM, word2vec, multitask learning, and the rise of GPT.
The article explains how the softmax activation function converts neural network outputs into probability distributions for multi‑class NLP tasks, describes its mathematical form and S‑shaped behavior, and discusses the inductive approach, data quality, training objectives, and interpretability challenges in deep learning language models.
The article explains Java's Object class as the root of all classes, details its fundamental methods such as clone, equals, hashCode, toString, finalize and getClass, illustrates shallow vs. deep copying, shows how to override equals with a Book example, and warns about using finalize for cleanup.
This tutorial explains how the super keyword invokes a superclass constructor—both no‑argument and parameterized—illustrates constructor chaining across inheritance hierarchies with concrete Java code examples, and highlights compilation errors when a matching superclass constructor is missing.
The article explains how Byte Pair Encoding (BPE) works as a greedy, linear‑time subword segmentation technique, walks through its step‑by‑step token merging process with a concrete sentence example, discusses its strengths in handling OOV words, and outlines its limitations and alternatives such as WordPiece and SentencePiece.
This tutorial demonstrates how the super keyword lets a subclass invoke overridden methods and access shadowed fields in its superclass, providing step‑by‑step Java code examples, execution results, and explanations of the underlying inheritance mechanics.
