Machine learning books and papers

​​ByT5: Towards a token-free future with pre-trained byte-to-byte models Pre-trained language models usually operate on the sequences of tokens, which are based on words or subword units. Token-free models operate directly on the raw text (characters or bytes) instead. They can work with any language, are more robust to the noise, and don’t require preprocessing. The authors use a modified mT5 architecture and show that their approach is competitive with token-level models. Paper: https://arxiv.org/abs/2105.13626 Code: https://github.com/google-research/byt5 A detailed unofficial overview of the paper: https://andlukyane.com/blog/paper-review-byt5 #nlp #deeplearning #transformer #pretraining @Machine_learn

با عرض سلام ما پكيج ٣٦ پروژه عملي با يادگيري عميق همراه با داكيومنت فارسي را براي دوستاني كه مي خواهند در اين حوزه به صورت عملي كار كنند تهيه كرديم سرفصل هاي اين پكيج به ترتيب زير مي باشند: 1-Deep Learning Basic -01_Introduction --01_How_TensorFlow_Works --02_Creating_and_Using_Tensors --03_Implementing_Activation_Functions -02_TensorFlow_Way --01_Operations_as_a_Computational_Graph --02_Implementing_Loss_Functions --03_Implementing_Back_Propagation --04_Working_with_Batch_and_Stochastic_Training --05_Evaluating_Models -03_Linear_Regression --linear regression --Logistic Regression -04_Neural_Networks --01_Introduction --02_Single_Hidden_Layer_Network --03_Using_Multiple_Layers -05_Convolutional_Neural_Networks --Convolution Neural Networks --Convolutional Neural Networks Tensorflow --TFRecord For Deep learning Models -06_Recurrent_Neural_Networks --Recurrent Neural Networks (RNN) 2-Classification apparel -Classification apparel double capsule -Classification apparel double cnn 3-ALZHEIMERS USING CNN(ResNet) 4-Fake News (Covid-19 dataset) -Multi-channel -3DCNN model -Base line+ Char CNN -Fake News Covid CapsuleNet 5-3DCNN Fake News 6-recommender systems -GRU+LSTM MovieLens 7-Multi-Domain Sentiment Analysis -Dranziera CapsuleNet -Dranziera CNN Multi-channel -Dranziera LSTM 8-Persian Multi-Domain SA -Bi-GRU Capsule Net -Multi-CNN 9-Recommendation system -Factorization Recommender, Ranking Factorization Recommender, Item Similarity Recommender (turicreate) -SVD, SVD++, NMF, Slope One, k-NN, Centered k-NN, k-NN Baseline, Co-Clustering(surprise) 10-NihX-Ray -optimized CNN on FullDataset Nih-Xray -MobileNet -Transfer learning -Capsule Network on FullDataset Nih-Xray هزينه اين پكيج ٥٠٠هزار مي باشد و صرفا هزينه تهيه ديتاست هاست. جهت خريد مي توانيد با ايدي بنده در ارتباط باشيد @Raminmousa

Github: https://github.com/OlafenwaMoses/DeepStack_ExDark Documentation: https://docs.deepstack.cc/index.html#installation Custom dataset preparation: https://docs.deepstack.cc/custom-models/datasetprep/index.html Training custom model: https://docs.deepstack.cc/custom-models/training/index.html @Machine_learn

Graph Convolutional Neural Networks to Analyze Complex Carbohydrates A blog post by Daniel Bojar about an application of GNN to analyzing glycan sequences and their proposed GNN architecture called SweetNet. There are other coverages of this work (here and here). The paper is here and the code is here. @Machine_learn

Tokyo Olympics Alternative medals table Article on how teams performed with the respect to behavior expected by regression model. Link: https://ig.ft.com/tokyo-olympics-alternative-medal-table/ @Machine_learn

Paper: https://arxiv.org/pdf/2107.10833v1.pdf Github: https://github.com/xinntao/Real-ESRGAN Colab demo: https://colab.research.google.com/drive/1k2Zod6kSHEvraybHl50Lys0LerhyTMCo?usp=sharing @Machine_learn

🥑 DALL·E Mini Generate images from a text prompt Demo: https://huggingface.co/spaces/flax-community/dalle-mini Github: https://github.com/borisdayma/dalle-mini Paper: https://wandb.ai/dalle-mini/dalle-mini/reports/DALL-E-mini--Vmlldzo4NjIxODA @Machine_learn

با عرض سلام ما پكيج ٣٦ پروژه عملي با يادگيري عميق همراه با داكيومنت فارسي را براي دوستاني كه مي خواهند در اين حوزه به صورت عملي كار كنند تهيه كرديم سرفصل هاي اين پكيج به ترتيب زير مي باشند: 1-Deep Learning Basic -01_Introduction --01_How_TensorFlow_Works --02_Creating_and_Using_Tensors --03_Implementing_Activation_Functions -02_TensorFlow_Way --01_Operations_as_a_Computational_Graph --02_Implementing_Loss_Functions --03_Implementing_Back_Propagation --04_Working_with_Batch_and_Stochastic_Training --05_Evaluating_Models -03_Linear_Regression --linear regression --Logistic Regression -04_Neural_Networks --01_Introduction --02_Single_Hidden_Layer_Network --03_Using_Multiple_Layers -05_Convolutional_Neural_Networks --Convolution Neural Networks --Convolutional Neural Networks Tensorflow --TFRecord For Deep learning Models -06_Recurrent_Neural_Networks --Recurrent Neural Networks (RNN) 2-Classification apparel -Classification apparel double capsule -Classification apparel double cnn 3-ALZHEIMERS USING CNN(ResNet) 4-Fake News (Covid-19 dataset) -Multi-channel -3DCNN model -Base line+ Char CNN -Fake News Covid CapsuleNet 5-3DCNN Fake News 6-recommender systems -GRU+LSTM MovieLens 7-Multi-Domain Sentiment Analysis -Dranziera CapsuleNet -Dranziera CNN Multi-channel -Dranziera LSTM 8-Persian Multi-Domain SA -Bi-GRU Capsule Net -Multi-CNN 9-Recommendation system -Factorization Recommender, Ranking Factorization Recommender, Item Similarity Recommender (turicreate) -SVD, SVD++, NMF, Slope One, k-NN, Centered k-NN, k-NN Baseline, Co-Clustering(surprise) 10-NihX-Ray -optimized CNN on FullDataset Nih-Xray -MobileNet -Transfer learning -Capsule Network on FullDataset Nih-Xray هزينه اين پكيج ٥٠٠هزار مي باشد و صرفا هزينه تهيه ديتاست هاست. جهت خريد مي توانيد با ايدي بنده در ارتباط باشيد @Raminmousa

A Dataset for Studying Gender Bias in Translation http://ai.googleblog.com/2021/06/a-dataset-for-studying-gender-bias-in.html @Machine_learn

🌠 Deepmind's Generally capable agents emerge from open-ended play Blog : https://deepmind.com/blog/article/generally-capable-agents-emerge-from-open-ended-play Paper: https://deepmind.com/research/publications/open-ended-learning-leads-to-generally-capable-agents DeepMind Research: https://github.com/deepmind/deepmind-research Video: https://www.youtube.com/watch?v=lTmL7jwFfdw&ab_channel=DeepMind @Machine_learn

🔸لیستی از برترین کانال‌های آموزشی در زمینه های هوش‌مصنوعی, پایتون و یادگیری ماشین ‏❯ هوش مصنوعی: 1️⃣ @Ai_Tv 2️⃣ @AI_PYTHON 3️⃣ @HomeAI ‏❯ علم داده : 1⃣ @DataAnalysis 2⃣ @SQL_Server ‏❯ یادگیری ماشین و یادگیری عمیق : 1️⃣ @Machine_learn ‏❯ آموزش پایتون : 1⃣ @pythonchallenge 2⃣ @raspberry_python 3⃣ @python4finance 4⃣ @Programming4all_0to100

سلام دوستانی که با بنده پایان نامه برداشتن یا من به عنوان مشاورشون هستم حتما این مجموعه رو تهیه کنن.

Cartoon-StyleGan2 🙃 : Fine-tuning StyleGAN2 for Cartoon Face Generation Github: https://github.com/happy-jihye/Cartoon-StyleGan2 Paper: https://arxiv.org/abs/2106.12445 Colab: https://colab.research.google.com/github/happy-jihye/Cartoon-StyleGan2/blob/main/Cartoon_StyleGAN2.ipynb @Machine_learn

Deep Learning Dataset For Passage and Document Retrieval Github: https://github.com/grill-lab/DL-Hard Paper: https://arxiv.org/abs/2105.07975v1 @Machine_learn

EL-Attention: Memory Efficient Lossless Attention for Generation Github: https://github.com/microsoft/fastseq Paper: https://arxiv.org/abs/2105.04779v1 @Machine_learn