FreezeD: A Simple Baseline for Fine-tuning GANs
Simple Baseline for Fine-Tuning GANs
Code: https://github.com/sangwoomo/freezeD
Paper: https://arxiv.org/abs/2002.10964
Datasets: https://vcla.stat.ucla.edu/people/zhangzhang-si/HiT/exp5.html
Simple Baseline for Fine-Tuning GANs
Code: https://github.com/sangwoomo/freezeD
Paper: https://arxiv.org/abs/2002.10964
Datasets: https://vcla.stat.ucla.edu/people/zhangzhang-si/HiT/exp5.html
Imbalanced Classification Model to Detect Mammography Microcalcifications
https://machinelearningmastery.com/imbalanced-classification-model-to-detect-microcalcifications/
https://machinelearningmastery.com/imbalanced-classification-model-to-detect-microcalcifications/
MachineLearningMastery.com
Imbalanced Classification Model to Detect Mammography Microcalcifications - MachineLearningMastery.com
Cancer detection is a popular example of an imbalanced classification problem because there are often significantly more cases of non-cancer than actual cancer.
A standard imbalanced classification dataset is the mammography dataset that involves detecting…
A standard imbalanced classification dataset is the mammography dataset that involves detecting…
Fast and Three-rious: Speeding Up Weak Supervision with Triplet Methods
FlyingSquid is a new framework for automatically building models from multiple noisy label sources.
Code: https://github.com/HazyResearch/flyingsquid
Blog: https://hazyresearch.stanford.edu/flyingsquid
Paper: https://arxiv.org/abs/2002.11955v1
FlyingSquid is a new framework for automatically building models from multiple noisy label sources.
Code: https://github.com/HazyResearch/flyingsquid
Blog: https://hazyresearch.stanford.edu/flyingsquid
Paper: https://arxiv.org/abs/2002.11955v1
160+ Data Science Interview Questions
https://hackernoon.com/160-data-science-interview-questions-415s3y2a
https://hackernoon.com/160-data-science-interview-questions-415s3y2a
Hackernoon
160+ Data Science Interview Questions | HackerNoon
A typical interview process for a data science position includes multiple rounds. Often, one of such rounds covers theoretical concepts, where the goal is to determine if the candidate knows the fundamentals of machine learning.
Meta-Transfer Learning for Zero-Shot Super-Resolution
Code: https://github.com/JWSoh/MZSR
Paper: https://arxiv.org/abs/2002.12213v1
Code: https://github.com/JWSoh/MZSR
Paper: https://arxiv.org/abs/2002.12213v1
Better scalability with Cloud TPU pods and TensorFlow 2.1
https://cloud.google.com/blog/products/ai-machine-learning/better-scalability-with-cloud-tpu-pods-and-tensorflow-2-1
TensorFlow Official Models: https://github.com/tensorflow/models/tree/master/official
https://cloud.google.com/blog/products/ai-machine-learning/better-scalability-with-cloud-tpu-pods-and-tensorflow-2-1
TensorFlow Official Models: https://github.com/tensorflow/models/tree/master/official
Google Cloud Blog
Cloud TPU Pods generally available, now include TensorFlow 2.1 support | Google Cloud Blog
Cloud TPU Pods are now generally available, and include TensorFlow 2.1 support and other new features.
This media is not supported in your browser
VIEW IN TELEGRAM
Deep Image Spatial Transformation for Person Image Generation
Pose-guided person image generation is to transform a source person image to a target pose.
Github: https://github.com/RenYurui/Global-Flow-Local-Attention
Paper: https://arxiv.org/abs/2003.00696v1
Pose-guided person image generation is to transform a source person image to a target pose.
Github: https://github.com/RenYurui/Global-Flow-Local-Attention
Paper: https://arxiv.org/abs/2003.00696v1
Sign Language Recognition with Deep Learning and PyTorch
https://theaisummer.com/Sign-Language-Recognition-with-PyTorch/
https://theaisummer.com/Sign-Language-Recognition-with-PyTorch/
MARKOV CHAIN MONTE CARLO (MCMC) SAMPLING
https://www.tweag.io/posts/2019-10-25-mcmc-intro1.html
Habr ru: https://habr.com/ru/company/piter/blog/491268/
https://www.tweag.io/posts/2019-10-25-mcmc-intro1.html
Habr ru: https://habr.com/ru/company/piter/blog/491268/
A software toolkit for research on general-purpose text understanding models
jiant is a software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks
https://jiant.info/
Code: https://github.com/nyu-mll/jiant
Paper: https://arxiv.org/pdf/2003.02249v1.pdf
jiant is a software toolkit for natural language processing research, designed to facilitate work on multitask learning and transfer learning for sentence understanding tasks
https://jiant.info/
Code: https://github.com/nyu-mll/jiant
Paper: https://arxiv.org/pdf/2003.02249v1.pdf
GitHub
GitHub - nyu-mll/jiant: jiant is an nlp toolkit
jiant is an nlp toolkit. Contribute to nyu-mll/jiant development by creating an account on GitHub.
Simulating the Universe in TensorFlow
https://blog.tensorflow.org/2020/03/simulating-universe-in-tensorflow.html
https://blog.tensorflow.org/2020/03/simulating-universe-in-tensorflow.html
This media is not supported in your browser
VIEW IN TELEGRAM
Measuring Compositional Generalization
https://ai.googleblog.com/2020/03/measuring-compositional-generalization.html
https://ai.googleblog.com/2020/03/measuring-compositional-generalization.html
Step-By-Step Framework for Imbalanced Classification Projects
https://machinelearningmastery.com/framework-for-imbalanced-classification-projects/
https://machinelearningmastery.com/framework-for-imbalanced-classification-projects/
MachineLearningMastery.com
Step-By-Step Framework for Imbalanced Classification Projects - MachineLearningMastery.com
Classification predictive modeling problems involve predicting a class label for a given set of inputs. It is a challenging problem in general, especially if little is known about the dataset, as there are tens, if not hundreds, of machine learning algorithms…
Action Segmentation with Joint Self-Supervised Temporal Domain Adaptation (PyTorch)
Code: https://github.com/cmhungsteve/SSTDA
Paper: https://arxiv.org/abs/2003.02824
Code: https://github.com/cmhungsteve/SSTDA
Paper: https://arxiv.org/abs/2003.02824
🎇Announcing TensorFlow Quantum: An Open Source Library for Quantum Machine Learning
https://ai.googleblog.com/2020/03/announcing-tensorflow-quantum-open.html
https://ai.googleblog.com/2020/03/announcing-tensorflow-quantum-open.html
Lagrangian Neural Networks
In contrast to Hamiltonian Neural Networks, these models do not require canonical coordinates and perform well in situations where generalized momentum is difficult to compute
Code: https://github.com/MilesCranmer/lagrangian_nns
Paper: https://arxiv.org/abs/2003.04630v1
In contrast to Hamiltonian Neural Networks, these models do not require canonical coordinates and perform well in situations where generalized momentum is difficult to compute
Code: https://github.com/MilesCranmer/lagrangian_nns
Paper: https://arxiv.org/abs/2003.04630v1
Google just announced their new TensorFlow Developer Certificate, which is a great way to showcase your TF skills. Check it out
https://www.tensorflow.org/certificate
https://www.tensorflow.org/certificate
TensorFlow
Receive the TensorFlow Developer Certificate - TensorFlow
Demonstrate your level of proficiency in using TensorFlow to solve deep learning and ML problems by passing the TensorFlow Certificate program.
On the Texture Bias for Few-Shot CNN Segmentation
This repository contains the code for deep auto-encoder-decoder network for few-shot semantic segmentation with state of the art results on FSS 1000 class dataset and Pascal 5i
Code: https://github.com/rezazad68/fewshot-segmentation
Paper: https://arxiv.org/abs/2003.04052v1
Download 1000-class dataset
This repository contains the code for deep auto-encoder-decoder network for few-shot semantic segmentation with state of the art results on FSS 1000 class dataset and Pascal 5i
Code: https://github.com/rezazad68/fewshot-segmentation
Paper: https://arxiv.org/abs/2003.04052v1
Download 1000-class dataset
This media is not supported in your browser
VIEW IN TELEGRAM
🌐 Fast and Easy Infinitely Wide Networks with Neural Tangents
Neural Tangents is a high-level neural network API for specifying complex, hierarchical, neural networks of both finite and infinite width. Neural Tangents allows researchers to define, train, and evaluate infinite networks as easily as finite ones.
https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-wide-networks.html
Colab notebook: https://colab.research.google.com/github/google/neural-tangents/blob/master/notebooks/neural_tangents_cookbook.ipynb#scrollTo=Lt74vgCVNN2b
Code: https://github.com/google/neural-tangents
Paper: https://arxiv.org/abs/1912.02803
Neural Tangents is a high-level neural network API for specifying complex, hierarchical, neural networks of both finite and infinite width. Neural Tangents allows researchers to define, train, and evaluate infinite networks as easily as finite ones.
https://ai.googleblog.com/2020/03/fast-and-easy-infinitely-wide-networks.html
Colab notebook: https://colab.research.google.com/github/google/neural-tangents/blob/master/notebooks/neural_tangents_cookbook.ipynb#scrollTo=Lt74vgCVNN2b
Code: https://github.com/google/neural-tangents
Paper: https://arxiv.org/abs/1912.02803
FastText: stepping through the code
fastText is a library for efficient learning of word representations and sentence classification.
Article: https://medium.com/@mariamestre/fasttext-stepping-through-the-code-259996d6ebc4
Habr ru: https://habr.com/ru/post/492432/
Code: https://github.com/facebookresearch/fastText
fastText is a library for efficient learning of word representations and sentence classification.
Article: https://medium.com/@mariamestre/fasttext-stepping-through-the-code-259996d6ebc4
Habr ru: https://habr.com/ru/post/492432/
Code: https://github.com/facebookresearch/fastText
Medium
FastText: stepping through the code
Little disclaimer: some of the information in this blog post might be incorrect. It will most probably become out-of-date very soon too. In…