Swortal

最近读了两本美国国父的书， 一本是 Founding Fathers: The Essential Guide to the Men Who Made America by The Encyclopaedia Britannica 这本书介绍了20 - 30位美国国父，他们大多参与过独立战争、立宪会议以及美国建国的整个过程。大部分人的介绍都很短，主要是简单履历，大部分都是律师和政府官员，然后反对英国加税。少数重要人物比如华盛顿会有长的多的篇幅介绍。 第二本是 Founding Brothers: The Revolutionary Generation (Pulitzer Prize Winner) by Joseph J. Ellis 这本书主要聚焦于几个最重要国父：华盛顿、汉密尔顿、亚当斯、杰斐逊、麦迪逊、富兰克林，讲述了他们之间的六个重要事件：汉密尔顿最终的决斗，麦迪逊和汉密尔顿在一个晚餐上达成的首都选址和国家债务的协议，废除奴隶制的大讨论，华盛顿的退休，杰斐逊和亚当斯的交恶，杰斐逊和亚当斯晚年深刻展示他们政治思想的信件往来，从这六个事件出发分析了它们背后美国的建国背景和当时的环境。 这两本书让我以小见大，从国父的故事中窥见了美国独立建国的大历史，感受很深，就把映像最深刻的一些点按照我自己的逻辑写出来，有些是直接摘抄书中的内容。 美国国父们的自然神论信仰 Deist 虽然美国是新教国家，大部分国父也成长于天主教地区，但在18世纪的美国，一种名为自然神论（Deism）的宗教思想流派的广泛存在，使得国父们的真实信仰变得更加复杂。自然神论汲取了让-雅克·卢梭（Jean-Jacques Rousseau）、艾萨克·牛顿（Isaac Newton）和约翰·洛克（John Locke）等人的科学与哲学成果，主张人类的经验和理性——而非宗教教条与神秘主义——决定信仰的合理性。 自然神论不可避免地颠覆了正统基督教。受这一思潮影响的人们几乎没有理由去阅读《圣经》、祈祷、上教堂，或参与诸如洗礼、圣餐、主教按手礼（坚振礼）等宗教仪式。 从18世纪中叶到19世纪，自然神论在大学中极为盛行，因此影响了革命时代许多受过教育（以及未受教育）的男性。这些人在大学毕业后通常会继续在公开场合保持基督徒身份，但内心可能持有非正统的宗教观点。 尽管在新共和国的各个阶段都有...

 感恩时节沐早雨，忽而放晴踏红叶。 年关将至枝丫秃，偶有簇红难掩寥。 乔林竟落华市隅，千年相伴令人羡。 嗜书行善馈馆阁，人间烟火无洋汉。

 Source:  https://youtu.be/yBL7J0kgldU?si=koiBhKpq3Cp1M8G7 research methodology deconstruct into building blocks, structure, knowledge, reasoning etc.. study in controlled way, idealized environment, control the data, tweak the params highly repeatable experiments 100m size model, universal laws 1xH100 within a day probe inner working knowledge extraction 2 types of data biography of N individuals QA data to extract the fact of the N individuals based on Biography Training data: N biographies, + N/2 QA data Test data: the other N/2 QA data If the model can perform well on the other N/2 individuals’ biography questions, then it has knowledge extraction capability Option 1: Pre train with both N biographies and N/2 QA result: good knowledge extraction Option 2: Pre train with biography data only, fine tune with QA result: bad knowledge extraction Option 3: augment the biography data for each person, pretrain with biography and fine tune with QA ...

  Personal highlights Memory movement is more expensive than computation Network latency is more significant than computation with same memory consumption, we want the network to have as much computation as possible to increase accuracy Common technique: Pruning, Quantization, Distillation different level of grouping and granularity used in pruning, quantization, parallel execution Common evaluation and optimization criteria weight significance, activation significance, tensor wise, channel wise, batch wise … l2 loss, KL divergence, accuracy, latency, number of computation, memory usage Common ideas to optimize a neural network structure using above techniques architecture option as a trainable parameter and additional loss or KD divergence Optimize the architecture params with regular weights either together or freeze one and optimize the other iteratively iteratively prune/ quantize / distill and evaluate after fine tune in each round abrasion study, delete...