[{"data":1,"prerenderedAt":267},["ShallowReactive",2],{"project-10168101":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":28,"sentiment":29,"stance_mix":30,"scored_comments":35,"aspects":36,"strip":43,"post_text":45,"what":46,"said":82,"maker_in_thread":163,"shape":167,"grid":172,"attempts":229,"same_week":230,"maker_shows":33,"maker_hidden":260,"reader_version":261,"card":262},"10168101","ann-writer","Neural network that impersonates writers","title","Show HN: Neural network that impersonates writers","https:\u002F\u002Fgithub.com\u002FJacobPlaster\u002Fann-writer","github.com","jacob_plaster",1441323285,2015,48,27,590,2565,24,"shown","ai","text generation","library",[21,24,25,26,27],"neural network","sklearn","writing style","markov chain","roasted",-0.31,{"positive":31,"neutral":32,"mixed":33,"critical":34},2,3,1,13,19,{"performance":37,"execution":39,"idea":41,"docs":42},{"positive":38,"critical":32},0,{"positive":38,"critical":40},7,{"positive":33,"critical":31},{"positive":38,"critical":33},[33,33,33,33,33,32,38,33,33,33,32,33,33,32,33,33,38,32,38,38,38,33,44,38,44],5,null,{"problem":47,"audience":45,"pricing":45,"motivation":54,"time_to_build":45,"stack":61,"openness":79,"stage":80,"team_size":81},{"value":48,"source":49,"evidence":50},"Learns and imitates the writing style of an author.","maker",[51],{"id":52,"by":11,"text":53},"10170390","Good idea. I guess that was my main goal really, learning the structure of some text. The vocabulary generator was a pretty recent add in which is why it is quite in-accurate.",{"value":55,"source":49,"evidence":56},"Built for educational purposes to learn the structure of text.",[57,60],{"id":58,"by":11,"text":59},"10170430","I was confused with the difference between an SVM and a neural network. Easy mistake I guess. The whole goal of this project was for educational purposes, so im still happy with…",{"id":52,"by":11,"text":53},[62,70],{"value":63,"source":64,"evidence":65},"Python","inferred",[66],{"id":67,"by":68,"text":69},"10169230","strong_ai","this doesn't look like a neural net to me. from NeuralNetwork.py ``` from sklearn.neighbors import KNeighborsClassifier # Create a sperate neural network for each identifier for…",{"value":71,"source":72,"evidence":73},"scikit-learn","commenter",[74,75],{"id":67,"by":68,"text":69},{"id":76,"by":77,"text":78},"10171861","achompas","> I decided to use scikit's machine learning libraries. [...] The writer I create uses multiple SVM engines. One large neural network for the sentence structuring and multiple…","open_source","prototype","unknown",{"praise":83,"objections":99,"requests":132,"questions":141,"alternatives":149},[84],{"value":85,"source":72,"evidence":86},"Fun hack and good idea for matching house writing style",[87,91,95],{"id":88,"by":89,"text":90},"10168933","frisco","Fun hack. If anything, it highlights how compelling deep learning and RNNs are: no messing with NLP, no messing with building other features or adding up classifiers, etc. The…",{"id":92,"by":93,"text":94},"10169294","w_t_payne","I'd be interested to know if this could be turned into a tool that lets you know how well your writing (or coding) matches the \"house style\". (Mostly for technical documentation,…",{"id":96,"by":97,"text":98},"10169183","scorpwarp23","This is brilliant! I tried it out. Waiting for a larger data set! +1",[100,109,121],{"value":101,"source":72,"evidence":102},"Not a real neural network; it uses k-nearest neighbors classifiers",[103,104,108],{"id":67,"by":68,"text":69},{"id":105,"by":106,"text":107},"10169907","ching_wow_ka","So then it seems like the author of the code doesn't understand that \"NN\" means \"Nearest Neighbors\" and not \"Neural Network\"? He mentions that he used sklearn's Neural Network…",{"id":76,"by":77,"text":78},{"value":110,"source":72,"evidence":111},"Output quality is no better than a Markov chain",[112,116,120],{"id":113,"by":114,"text":115},"10168980","nl","I haven't looked at the code, but glancing at the results leaves me thinking it might need more work. The output seems to me around the level a Markov chain might produce.…",{"id":117,"by":118,"text":119},"10169050","Turing_Machine","I ran a Markov chain text generator on Finnegans Wake once. It came out looking much the same. :-)",{"id":88,"by":89,"text":90},{"value":122,"source":72,"evidence":123},"Copyright concerns over using Harry Potter text",[124,128],{"id":125,"by":126,"text":127},"10168952","caf","Have you considered the copyright on the Harry Potter training data?",{"id":129,"by":130,"text":131},"10169095","bhaak","I would still be cautious. There is no need to use exactly this text. Anyway, there are countries that don't have a fair use policy. So in this countries your repository could…",[133,137],{"value":134,"source":72,"evidence":135},"Larger training dataset",[136],{"id":96,"by":97,"text":98},{"value":138,"source":72,"evidence":139},"Tool to measure how closely writing matches a house style, possibly as a Sublime Text plugin",[140],{"id":92,"by":93,"text":94},[142],{"value":143,"source":72,"evidence":144},"Whether the normalization procedure was sound",[145],{"id":146,"by":147,"text":148},"10170982","bearzoo","I am afraid this author has no idea what he is doing - and is loosely throwing around terms he does not understand. What the hell was his normalization procedure. Dangerous to…",[150,155],{"value":151,"source":72,"evidence":152},"Karpathy's char-rnn",[153,154],{"id":113,"by":114,"text":115},{"id":88,"by":89,"text":90},{"value":156,"source":72,"evidence":157},"Markov chain text generators",[158,159],{"id":117,"by":118,"text":119},{"id":160,"by":161,"text":162},"10169923","kylebgorman","I just can't agree that a simple, linear-time operation like \"tokenizing words and basic n-gram models out of them\" is a tedious problem like you seem to be implying, nor do I…",{"comments":31,"answered":33,"key":164},[165,166],{"id":58,"text":59},{"id":52,"text":53},{"commenters":168,"max_depth":169,"maker_replies":31,"first_comment_mins":170,"lifespan_hours":171},17,4,347,47,[173,175,177,180,182,185,189,191,193,196,198,201,202,203,205,207,208,211,213,217,218,220,222,224,226],[113,38,33,174,114,38],"project\u002Fcritical\u002Fperformance",[67,33,33,176,68,38],"project\u002Fcritical\u002Fexecution",[178,33,33,179,114,38],"10169596","project\u002Fcritical\u002Fidea",[105,33,33,181,106,38],"project\u002Fcritical\u002Fdocs",[183,33,33,184,114,38],"10170058","maker\u002Fcritical\u002Fexecution",[186,33,32,187,188,38],"10170262","project\u002Fneutral\u002Fnone","lawlessone",[58,33,38,190,11,33],"maker\u002Fneutral\u002Fnone",[192,33,33,184,77,38],"10171897",[194,33,33,184,195,38],"10171957","GFK_of_xmaspast",[197,33,33,184,68,38],"10173209",[199,33,32,190,200,38],"10174910","stuxnet79",[146,31,33,184,147,38],[117,32,33,174,118,38],[88,169,32,204,89,38],"project\u002Fmixed\u002Fperformance",[206,169,33,174,114,38],"10169145",[160,169,33,179,161,38],[209,169,38,210,89,38],"10176220","commenter\u002Fneutral\u002Fidea",[125,44,32,212,126,38],"project\u002Fneutral\u002Fidea",[214,44,38,215,216,38],"10169036","other\u002Fneutral\u002Fnone","mccracken",[129,44,38,215,130,38],[219,44,38,215,216,38],"10169195",[76,221,33,184,77,38],6,[92,40,44,223,93,38],"project\u002Fpositive\u002Fidea",[52,40,38,225,11,33],"maker\u002Fpositive\u002Fidea",[96,227,44,228,97,38],8,"project\u002Fpositive\u002Fnone",[],[231,236,241,246,250,255],{"id":232,"name":233,"points":234,"category":235},"10180209","StarCraft",320,"games",{"id":237,"name":238,"points":239,"category":240},"10184982","Light Bootstrap Dashboard",170,"dev_tools",{"id":242,"name":243,"points":244,"category":245},"10171802","Libsoundio 1.0.0",129,"languages",{"id":247,"name":248,"points":249,"category":235},"10191997","Termloop",109,{"id":251,"name":252,"points":253,"category":254},"10182723","Bill Brown Dear Mom",91,"learning_science",{"id":256,"name":257,"points":258,"category":259},"10186440","Continuo",60,"productivity",false,"v2",{"id":263,"name":5,"line":6,"ai":260,"cat":20,"year":13,"points":14,"comments":15,"rec":28,"s":29,"top":18,"kw":264,"maker":11,"domain":10,"tier":19,"attempts":38,"strip":265,"url":9,"mix":266,"praise":85,"objection":101,"sub":21},10168101,[21,24,25,26,27],"1111130111311311030001505",[31,32,33,34],1794036535146]