Machine learning books and papers

AI & Art @Machine_learn some artist use the large collections of #data & #ML #algorithms to create mesmerizing & dynamic #installations watch the video —> https://youtu.be/I-EIVlHvHRM

Paper link: https://arxiv.org/pdf/1904.02689.pdf Github repo: https://github.com/dbolya/yolact

YOLACT (You Only Look At CoefficienTs) - Real-time Instance Segmentation Results are impressive, above 30 FPS on COCO test-dev

Practical Computer Vision Applications Using Deep Learning with CNNs — Ahmed Fawzy Gad (en) 2018 @Machine_learn

​​Uber AI Plug and Play Language Model (PPLM) PPLM allows a user to flexibly plug in one or more simple attribute models representing the desired control objective into a large, unconditional language modeling (LM). The method has the key property that it uses the LM as is – no training or fine-tuning is required – which enables researchers to leverage best-in-class LMs even if they don't have the extensive hardware required to train them. PPLM lets users combine small attribute models with an LM to steer its generation. Attribute models can be 100k times smaller than the LM and still be effective in steering it PPLM algorithm entails three simple steps to generate a sample: * given a partially generated sentence, compute log(p(x)) and log(p(a|x)) and the gradients of each with respect to the hidden representation of the underlying language model. These quantities are both available using an efficient forward and backward pass of both models; * use the gradients to move the hidden representation of the language model a small step in the direction of increasing log(p(a|x)) and increasing log(p(x)); * sample the next word more at paper: https://arxiv.org/abs/1912.02164 blogpost: https://eng.uber.com/pplm/ code: https://github.com/uber-research/PPLM online demo: https://transformer.huggingface.co/model/pplm @Machine_learn #nlp #lm #languagemodeling #uber #pplm

Learning Singing From Speech Article: https://arxiv.org/abs/1912.10128 Example: https://tencent-ailab.github.io/learning_singing_from_speech/

discriminative : 1:#Regression 2:#Logistic regression 3:#decision tree(Hunt) 4:#neural network(traditional network, deep network) 5:#Support Vector Machine(SVM) Generative: 1:#Hidden Markov model 2:#Naive bayes 3:#K-nearest neighbor(KNN) 4:#Generative adversarial networks(GANs) Deep learning: 1:CNN R_CNN Fast-RCNN Mask-RCNN 2:RNN 3:LSTM 4:CapsuleNet 5:Siamese: siamese cnn siamese lstm siamese bi-lstm siamese CapsuleNet 6:time series data SVR DT(cart) Random Forest linear Bagging Boosting جهت درخواست و راهنمایی در رابطه با پیاده سازی مقالات و پایان نامه ها در رابطه با مباحث deep learning و machine learning با ایدی زیر در ارتباط باشید @Raminmousa

@Machine_learn A new open benchmark for speech recognition with limited or no supervision https://ai.facebook.com/blog/a-new-open-benchmark-for-speech-recognition-with-limited-or-no-supervision/ Code and dataset: https://ai.facebook.com/tools/libri-light Full paper: https://arxiv.org/abs/1912.07875

T5: Text-To-Text Transfer Transformer Github: https://github.com/google-research/text-to-text-transfer-transformer Paper: https://arxiv.org/abs/1910.10683 @Machine_learn

Connections between Support Vector Machines, Wasserstein distance and gradient-penalty GANs https://arxiv.org/abs/1910.06922 SIte : https://ajolicoeur.wordpress.com/ Github : https://github.com/AlexiaJM/MaximumMarginGANs

GNNExplainer: Generating Explanations for Graph Neural Networks https://arxiv.org/abs/1903.03894 Github : https://github.com/RexYing/gnn-model-explainer/

👌Finding label errors in datasets and learning with noisy labels. https://github.com/cgnorthcutt/cleanlab/