[{"data":1,"prerenderedAt":376},["ShallowReactive",2],{"project-24332303":3},{"id":4,"name":5,"line":6,"line_source":7,"title":8,"url":9,"domain":10,"maker":11,"posted_at":12,"year":13,"points":14,"comments":15,"rank_in_year":16,"shown_in_year":17,"top":18,"tier":19,"category":20,"subcategory":21,"format":22,"keywords":23,"reception":29,"sentiment":30,"stance_mix":31,"scored_comments":35,"aspects":36,"strip":43,"post_text":46,"what":47,"said":92,"maker_in_thread":209,"shape":218,"grid":221,"attempts":339,"same_week":340,"maker_shows":39,"maker_hidden":369,"reader_version":370,"card":371},"24332303","ML From Scratch","free online textbook","title","Show HN: ML From Scratch – free online textbook","https:\u002F\u002Fdafriedman97.github.io\u002Fmlbook\u002Fcontent\u002Fintroduction.html","dafriedman97.github.io","dafrdman",1598886992,2020,259,54,180,3028,6,"legend","learning_science","machine learning textbook","other",[24,25,26,27,28],"machine learning","numpy","from scratch","linear regression","free textbook","curious",0.01,{"positive":18,"neutral":32,"mixed":33,"critical":34},14,0,4,24,{"docs":37,"design":40,"idea":41,"execution":42},{"positive":38,"critical":39},2,1,{"positive":33,"critical":39},{"positive":34,"critical":39},{"positive":33,"critical":39},[33,44,45,33,45,45,33,44,45,45,33,45,44,33,45,33,33,39,39,45,33,45,39,33,44,45,39,33,44,33,33,33,33,45,33,45,33,44,45,33],5,3,null,{"problem":48,"audience":55,"pricing":59,"motivation":65,"time_to_build":46,"stack":69,"openness":89,"stage":90,"team_size":91},{"value":49,"source":50,"evidence":51},"Existing ML textbooks skip the under-the-hood mathematical details of algorithms","maker",[52],{"id":53,"by":11,"text":54},"24332304","I'm linking to a free online book I just finished called Machine Learning from Scratch. The book aims to cover the complete, technical, \"under the hood\" details that other ML…",{"value":56,"source":50,"evidence":57},"Readers who want to understand ML algorithms mathematically and implement them",[58],{"id":53,"by":11,"text":54},{"value":60,"source":50,"evidence":61},"free",[62,64],{"id":63},"post",{"id":53,"by":11,"text":54},{"value":66,"source":50,"evidence":67},"Author wanted a book covering the under-the-hood details other ML texts skip",[68],{"id":53,"by":11,"text":54},[70,74,77,83],{"value":71,"source":50,"evidence":72},"Python",[73],{"id":53,"by":11,"text":54},{"value":25,"source":50,"evidence":75},[76],{"id":53,"by":11,"text":54},{"value":78,"source":50,"evidence":79},"scikit-learn",[80],{"id":81,"by":11,"text":82},"24336034","Perhaps I should have been clearer, but the \"code\" section within each chapter is not \"from scratch\". The \"construction\" section is \"from scratch\" in that it only uses numpy (not…",{"value":84,"source":50,"evidence":85},"JupyterBook",[86],{"id":87,"by":11,"text":88},"24334186","Yeah the book was built with JupyterBook. It's an awesome tool but I lose track of what it does to the .md files when creating the website.","open_source","launched","solo",{"praise":93,"objections":110,"requests":139,"questions":171,"alternatives":189},[94,106],{"value":95,"source":96,"evidence":97},"Good for readers who want to understand algorithms mathematically","commenter",[98,102],{"id":99,"by":100,"text":101},"24334058","stevesimmons","I have a different view :) I feel this book is the ideal companion for intermediate to advanced Python developers\u002Fdata scientists. People who know pandas pretty well, and so are…",{"id":103,"by":104,"text":105},"24333408","christinahope","Great resource! I’ve been looking for something with complete derivations all in one place. I've been looking for a while but haven't been able to find something like this.…",{"value":107,"source":96,"evidence":108},"Well-commented and rigorous presentation",[109],{"id":99,"by":100,"text":101},[111,122,129],{"value":112,"source":96,"evidence":113},"Relies on numpy, which can obscure how things work for beginners",[114,118],{"id":115,"by":116,"text":117},"24333791","fartcannon","Excellent! Very kind of you to do this. Are you accepting comments? If not, ignore the following. :) As someone who learned how to program from trial and error via tutorials on…",{"id":119,"by":120,"text":121},"24334110","infinitybeyond","I wholeheartedly agree with this. As a software developer without a strong math education, any time I open a \"from scratch\" ml learning resource, I immediately close it because I…",{"value":123,"source":96,"evidence":124},"Calling it from scratch is misleading since scikit-learn is used in code sections",[125],{"id":126,"by":127,"text":128},"24336000","atum47","That's a really cool initiative, but I think we disagree on the term \"from scratch\". Taking a look at the source code, I see you're using sklearn - which is a great tool - but,…",{"value":130,"source":96,"evidence":131},"Notation and some numpy functions are hard to follow",[132,136],{"id":133,"by":134,"text":135},"24333702","Cieric","Thanks for the summary, the object oriented stuff is fine in my mind. The trouble with the code comes from things like the numpy functions. I have experience in matrices for…",{"id":137,"by":11,"text":138},"24333095","The approach to this book is very similar to nnfs.io (a similar focus on deriving models from the bare bones). The biggest difference is that his focuses on deep learning while…",[140,147,154,161],{"value":141,"source":96,"evidence":142},"Add SVMs",[143],{"id":144,"by":145,"text":146},"24336100","bonoboTP","Looking through the topics, a useful addition would be SVMs.",{"value":148,"source":96,"evidence":149},"Downloadable epub or pdf version",[150],{"id":151,"by":152,"text":153},"24335421","shadowoflight","This looks fantastic! As a bit of a selfish question, have you considered also offering a downloadable epub of this book? I've been trying to keep my long-form digital reading to…",{"value":155,"source":96,"evidence":156},"Export raw code separate from notebooks",[157],{"id":158,"by":159,"text":160},"24333092","sgron","Just did a quick scan and looks pretty good! Would it be possible to add an option for exporting the raw code (maybe broken down by chapter\u002Fsection) separate from the notebooks?…",{"value":162,"source":96,"evidence":163},"Add a numpy appendix or more explanatory comments",[164,167],{"id":165,"by":11,"text":166},"24333953","Thanks so much for your feedback. Definitely open to comments! I agree 100% that any use of packages can be intimidating for newbies. I experimented at first with creating the…",{"id":168,"by":169,"text":170},"24337238","Bedon292","I think there is a balance to be struck. You should totally use numpy for the arrays and basic math applications. But say on the first example you use `self.X.T` what does `.T`…",[172,182],{"value":173,"source":96,"evidence":174},"Is the project open sourced and can it be licensed for company use?",[175,178],{"id":176,"by":169,"text":177},"24337268","You said in other comments that you used JupyterBook to make it. Would you consider open sourcing that so that others can contribute?",{"id":179,"by":180,"text":181},"24334884","ohuhu","I'd love to include the book to our company internal learning resources. Can you include an official license by any chance? Thank you",{"value":183,"source":96,"evidence":184},"How does it compare to Introduction to Statistical Learning or Elements of Statistical Learning?",[185],{"id":186,"by":187,"text":188},"24349706","beccaaf1229","This book is awesome! How does this compare to Introduction to Statistical Learning or Elements of Statistical Learning? Other than the addition of code?",[190,196,202],{"value":191,"source":96,"evidence":192},"nnfs.io (Neural Networks from Scratch)",[193],{"id":194,"by":134,"text":195},"24332867","First thing I thought of when I read the title was sentdex's nnfs.io (neural networks from scratch.) I don't have time to look at this in full right now, are there any major…",{"value":197,"source":50,"evidence":198},"Elements of Statistical Learning",[199],{"id":200,"by":11,"text":201},"24336057","I agree though I saw that as outside the scope of this book. I tried to be clear in the introduction that the book is a \"user manual\" of sorts that simply shows how to construct…",{"value":203,"source":96,"evidence":204},"fast.ai course",[205],{"id":206,"by":207,"text":208},"24336788","ABeeSea","I agree with you in theory. I really hate that the fast.ai course uses their own fast.ai library. Numpy is a bit different though as it “fixes” inefficiencies in Python’s typing…",{"comments":210,"answered":211,"key":212},20,11,[213,214,217],{"id":53,"text":54},{"id":215,"text":216},"24334044","Thanks for the catch! Ugh those pesky $$s. Changed it now. Looks like you found the repository. Do you think it would be enough to raise an issue there? (at…",{"id":87,"text":88},{"commenters":219,"max_depth":18,"maker_replies":210,"first_comment_mins":33,"lifespan_hours":220},26,51,[222,224,227,229,232,233,234,236,240,241,242,245,248,250,252,253,255,256,257,259,262,263,267,271,273,275,276,278,280,282,284,288,290,291,292,293,295,297,299,303,305,309,312,315,318,320,322,324,326,328,329,331,333,335],[53,33,33,223,11,39],"project\u002Fpositive\u002Fidea",[225,33,44,226,100,33],"24333919","project\u002Fpositive\u002Fdocs",[215,33,33,228,11,39],"maker\u002Fneutral\u002Fdocs",[230,33,45,231,100,33],"24334129","project\u002Fneutral\u002Fdocs",[87,33,33,231,11,39],[176,33,45,231,169,33],[115,39,45,235,116,33],"project\u002Fneutral\u002Fdesign",[237,39,33,238,239,33],"24333943","commenter\u002Fneutral\u002Fnone","abhayhegde",[165,39,33,235,11,39],[179,39,44,226,180,33],[243,39,33,244,11,39],"24335204","maker\u002Fneutral\u002Fnone",[246,39,45,235,247,33],"24335110","uoaei",[249,39,45,235,116,33],"24335130",[251,39,33,244,11,39],"24335207",[168,39,45,231,169,33],[254,39,33,231,11,39],"24337469",[99,39,44,223,100,33],[119,39,33,238,120,33],[258,39,33,238,145,33],"24340796",[260,39,45,235,261,33],"24334169","andi999",[206,39,33,238,207,33],[264,39,33,265,266,33],"24339375","other\u002Fneutral\u002Fnone","ninepoints",[268,38,39,269,270,33],"24335545","project\u002Fcritical\u002Fidea","legerdemain",[200,38,33,272,11,39],"project\u002Fneutral\u002Fidea",[126,45,39,274,127,33],"project\u002Fcritical\u002Fexecution",[81,45,33,231,11,39],[277,45,45,231,169,33],"24337183",[279,45,33,228,11,39],"24337484",[281,45,45,231,169,33],"24337851",[283,45,33,228,11,39],"24337920",[285,34,39,286,287,33],"24333230","project\u002Fcritical\u002Fdesign","maxerbubba",[289,34,33,235,11,39],"24333281",[103,44,44,223,104,33],[194,18,45,272,134,33],[137,18,33,231,11,39],[133,18,39,294,134,33],"project\u002Fcritical\u002Fdocs",[296,18,33,231,11,39],"24334080",[298,18,44,223,159,33],"24333110",[300,301,45,272,302,33],"24336109",7,"rizpanjwani",[304,301,33,272,11,39],"24342408",[306,307,33,265,308,33],"24335652",8,"zadkey",[310,307,33,265,311,33],"24335724","macintux",[313,307,33,265,314,33],"24336185","bjz_",[316,307,33,265,317,33],"24338261","mhh__",[151,319,45,231,152,33],9,[321,319,33,231,11,39],"24336004",[323,319,33,231,11,39],"24355924",[158,325,45,231,159,33],10,[327,325,33,231,11,39],"24333181",[186,211,44,223,187,33],[330,211,33,272,11,39],"24354349",[144,332,45,272,145,33],12,[334,332,33,272,11,39],"24336308",[336,337,33,265,338,33],"24335339",13,"ximeng",[],[341,345,350,355,359,364],{"id":342,"name":343,"points":344,"category":20},"24323589","WebRTC for the Curious",667,{"id":346,"name":347,"points":348,"category":349},"24304623","vscode-debug-visualizer",509,"dev_tools",{"id":351,"name":352,"points":353,"category":354},"24309237","Healthcare Is Dumb",441,"web_saas",{"id":356,"name":357,"points":358,"category":349},"24323378","Vimac",375,{"id":360,"name":361,"points":362,"category":363},"24305834","pantel.is",285,"games",{"id":365,"name":366,"points":367,"category":368},"24294397","Muse",266,"productivity",false,"v2",{"id":372,"name":5,"line":6,"ai":369,"cat":20,"year":13,"points":14,"comments":15,"rec":29,"s":30,"top":18,"kw":373,"maker":11,"domain":10,"tier":19,"attempts":33,"strip":374,"url":9,"mix":375,"praise":95,"objection":112,"sub":21},24332303,[24,25,26,27,28],"0530330533035030011303105310500003030530",[18,32,33,34],1794036595390]