Skip to content

Data Science & Machine Learning Newsletter # 85

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Ideas on inter­pret­ing machine learn­ing … Do I under­stand the model and answers my machine learn­ing algo­rithm is giv­ing me? And do I trust these answers? Unfor­tu­nately, the com­plex­ity that bestows the extra­or­di­nary pre­dic­tive abil­i­ties on machine learn­ing algo­rithms also makes the answers the algo­rithms pro­duce hard to under­stand, and maybe even hard to trust. … Free Machine Devamını Oku […]

Data Science & Machine Learning Newsletter # 84

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Recur­rent Neural Net­works — A Short Ten­sor­Flow Tuto­r­ial Deep Photo Style Trans­fer Code and data for paper “Deep Photo Style Trans­fer”: https://arxiv.org/abs/1703.07511 Here are some results from the algo­rithm (from left to right are input, style and our out­put):                   Evo­lu­tion Strate­gies: Devamını Oku […]

Data Science & Machine Learning Newsletter # 83

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Why is machine learn­ing ‘hard’? There have been tremen­dous advances made in mak­ing machine learn­ing more acces­si­ble over the past few years. … How­ever, machine learn­ing remains a rel­a­tively ‘hard’ prob­lem. There is no doubt the sci­ence of advanc­ing machine learn­ing algo­rithms through research is dif­fi­cult. Deep Learn­ing for Finance: Deep Port­fo­lios We explore the use Devamını Oku […]

Data Science & Machine Learning Newsletter # 82

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group How Multi­n­o­mial Logis­tic Regres­sion Model Works In the pool of super­vised clas­si­fi­ca­tion algo­rithms, the logis­tic regres­sion model is the first most algo­rithm to play with. This clas­si­fi­ca­tion algo­rithm again cat­e­go­rized into dif­fer­ent cat­e­gories. These cat­e­gories purely based on the num­ber of tar­get classes.  If the logis­tic regres­sion model used for address­ing the binary clas­si­fi­ca­tion Devamını Oku […]

Data Science & Machine Learning Newsletter # 81

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Google opens Data Stu­dio cus­tomized reports tool glob­ally to more than 180 mar­kets Google is open­ing its data ana­lyt­ics and visu­al­iza­tion tool Data Stu­dio to more than 180 coun­tries. 4 Strate­gies for Multi-Step Time Series Fore­cast­ing Time series fore­cast­ing is typ­i­cally dis­cussed where only a one-step pre­dic­tion is required.  What about when you need to pre­dict mul­ti­ple time Devamını Oku […]

Data Science & Machine Learning Newsletter # 80

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Python Envi­ron­ment for Time Series Fore­cast­ing Pre-trained word vec­tors “We are pub­lish­ing pre-trained word vec­tors for 90 lan­guages, trained on Wikipedia using fast­Text. These vec­tors in dimen­sion 300 were obtained using the skip-gram model described in 1 with default para­me­ters. ” On the Ori­gin of Deep Learn­ing This paper is a review of the evo­lu­tion­ary his­tory of deep Devamını Oku […]

Data Science & Machine Learning Newsletter # 79

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Pre­pro­cess­ing for Machine Learn­ing with tf.Transform When apply­ing machine learn­ing to real world datasets, a lot of effort is required to pre­process data into a for­mat suit­able for stan­dard machine learn­ing mod­els, .…  Today we are announc­ing tf.Transform, a library for Ten­sor­Flow that allows users to define pre­pro­cess­ing pipelines and run these using large scale data pro­cess­ing Devamını Oku […]

Data Science & Machine Learning Newsletter # 78

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Machine Learn­ing in Cyber Secu­rity Domain 1: Fun­da­men­tals 2: Cyber Secu­rity Rat­ing and Inci­dent Fore­cast­ing 3: Fraud Detec­tion 4: Secure User Authen­ti­ca­tion NanoNets : How to use Deep Learn­ing when you have Lim­ited Data  One com­mon bar­rier for using deep learn­ing to solve prob­lems is the amount of data needed to train a model. Anonymiz­ing doc­u­ments with Word Vec­tors Devamını Oku […]

Data Science & Machine Learning Newsletter # 77

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Train­ing a deep learn­ing model to steer a car in 99 lines of code Deep learn­ing in 2017 is mag­i­cal. We get to apply immensely com­plex algo­rithms to equally com­plex prob­lems with­out hav­ing to spend all our time writ­ing the algo­rithms our­selves. Instead, thanks to libraries like Ten­sor­Flow and Keras, we get to focus on the fun stuff: model archi­tec­ture, para­me­ter tun­ing and data aug­men­ta­tion. Com­pre­hen­sive Devamını Oku […]

Data Science & Machine Learning Newsletter # 76

You want to get updates? Please join Data Sci­ence & Machine Learn­ing Newslet­ter Linked Group Domain Trans­fer Net­work (DTN) Ten­sor­Flow imple­men­ta­tion of Unsu­per­vised Cross-Domain Image Gen­er­a­tion. Mas­ter­ing the Game of Go with Deep Neural Net­works and Tree Search Google Deep­Mind paper A Sur­vey on Trans­fer Learn­ing A major assump­tion in many machine learn­ing and data min­ing algo­rithms is that the train­ing and future data must be in the same fea­ture space and Devamını Oku […]