paulo.difficiliora - un po' più difficile ?

http://people.ee.ethz.ch/~ihnatova/ Inviato dal mio smartphone LG

https://medium.com/towards-data-science/how-to-train-your-own-object-detector-with-tensorflows-object-detector-api-bec72ecfe1d9 Inviato dal mio smartphone LG

Regressione Logistica - Logistic Regression Analisi del problema MINST (poi capiremo come viene implementata) https://www.kdnuggets.com/2016/07/softmax-regression-related-logistic-regression.html Logistic Regression = BINARY CLASSIFICATION SoftMax Regression = Multi-Class Classification (mutualmente esclusive altrimenti è necessario utilizzare un'altra funzione di minimizzazione) Nota :  https://stackoverflow.com/questions/34240703/whats-the-difference-between-softmax-and-softmax-cross-entropy-with-logits (Edited 2016-02-07: If you have single-class labels, where an object can only belong to one class, you might now consider using   tf.nn.sparse_softmax_cross_entropy_with_logits   so that you don't have to convert your labels to a dense one-hot array. This function was added after release 0.6.0.) Analisi del problema MINST (poi capiremo come viene implementata) Immagini 28 x 28 = 784 array  LABEL per la classificazione =  One Hot Array è [1,0, ... 0]  (10 elementi) (un 1 dove è...

https://codelabs.developers.google.com/

http://maxmelnick.com/2016/07/04/visualizing-tensorflow-retrain.html Inviato dal mio smartphone LG

https://pythonmachinelearning.pro/perceptrons-the-first-neural-networks/ Inviato dal mio smartphone LG

https://www.svm-tutorial.com/2017/10/support-vector-machines-succinctly-released/ Inviato dal mio smartphone LG

https://medium.com/@akimach/hand-gesture-recognition-on-ios-11-using-coreml-and-keras-f943db648f75 Inviato dal mio smartphone LG

A standard approach is to scale the inputs to have mean 0 and a variance of 1. Also linear decorrelation/whitening/pca helps a lot. 1- Min-max normalization retains the original distribution of scores except for a scaling factor and transforms all the scores into a common range [0, 1]. However, this method is not  robust (i.e., the method is highly sensitive to outliers. 2- Standardization (Z-score normalization) The most commonly used technique, which is calculated using the arithmetic mean and standard deviation of the given data. However, both mean and standard deviation are sensitive to outliers, and this technique does not guarantee a common numerical range for the normalized scores. Moreover, if the input scores are not Gaussian distributed, this technique does not retain the input distribution at the output. 3- Median and MAD: The median and median absolute deviation (MAD) are insensitive to outliers and the points in the extreme tails of the distribution. therefore it is robust...

Tf DataSet and Estimator https://developers.googleblog.com/2017/09/introducing-tensorflow-datasets.html?m=1 Dati da utilizzare per i test https://stat.ethz.ch/R-manual/R-devel/library/datasets/html/mtcars.html Machine Learning CookBook with Tensorflow - Book https://github.com/nfmcclure/tensorflow_cookbook TensorFlow Getting Started https://www.katacoda.com/basiafusinska/courses/tensorflow-getting-started High-level Learn Module in TensorFlow https://terrytangyuan.github.io/2016/06/09/scikit-flow-v09/ Regressione Lineare con TensorFlow https://aqibsaeed.github.io/2016-07-07-TensorflowLR/ Evernote consente di ricordare tutto e di organizzarti senza sforzo. Scarica Evernote .

Word2vec è un modello (evoluzione Doc2vec) https://sourcedexter.com/tensorflow-text-classification/ https://github.com/tflearn/tflearn Vector space models   (VSMs) represent (embed) words in a continuous vector space where semantically similar words are mapped to nearby points ('are embedded nearby each other') Word2vec is a particularly computationally-efficient predictive model for learning word embeddings from raw text. It comes in two flavors, the Continuous Bag-of-Words model (CBOW) and the Skip-Gram model (Section 3.1 and 3.2 in   Mikolov et al. ) Skip Gram Model http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/ Bag-Of-Words Model https://ongspxm.github.io/blog/2014/12/bag-of-words-natural-language-processing/ Il modello è semplice perchè usa un trucco del auto-encoder l'output layer fa deve ritornare la stessa cosa dell'input (apprendimento supervisionato anche se non si hanno le label) poi si rimuove il livello di output e si ottengono i p...

Appunti di viaggio