This media is not supported in your browser
VIEW IN TELEGRAM
🦑 Нейроэволюция киберкальмаров
Для создания нейронных сетей, обеспечивающих поведение без обучения, можно использовать нейроэволюцию. Эволюционные алгоритмы (например, такой, который я использовал для выполнения эволюции растений) подвергают генетический код эволюции в течение долгого периода времени. Генетический код (модель для ДНК) и представляемый им организм изначально очень просты, но в течение многих поколений небольшие мутации увеличивают благоприятную сложность и добавляют функции, стимулирующие дальнейшее распространение этих свойств.
Цифровые кальмары
Чтобы продемонстрировать действие нейроэволюции, я хочу подвергнуть эволюции цифровых кальмаров. Кальмары обладают следующими свойствами:
➡️ Читать дальше :
🔩 Код из статьи
@ai_machinelearning_big_data
Для создания нейронных сетей, обеспечивающих поведение без обучения, можно использовать нейроэволюцию. Эволюционные алгоритмы (например, такой, который я использовал для выполнения эволюции растений) подвергают генетический код эволюции в течение долгого периода времени. Генетический код (модель для ДНК) и представляемый им организм изначально очень просты, но в течение многих поколений небольшие мутации увеличивают благоприятную сложность и добавляют функции, стимулирующие дальнейшее распространение этих свойств.
Цифровые кальмары
Чтобы продемонстрировать действие нейроэволюции, я хочу подвергнуть эволюции цифровых кальмаров. Кальмары обладают следующими свойствами:
@ai_machinelearning_big_data
Please open Telegram to view this post
VIEW IN TELEGRAM
Jukebox: a new generative model for audio from OpenAI.
Jukebox, a model that generates music with singing in the raw audio domain.
openai.com/blog/jukebox
Article: cdn.openai.com/papers/jukebox.pdf
Examples: https://jukebox.openai.com/
Code: https://github.com/openai/jukebox
Jukebox, a model that generates music with singing in the raw audio domain.
openai.com/blog/jukebox
Article: cdn.openai.com/papers/jukebox.pdf
Examples: https://jukebox.openai.com/
Code: https://github.com/openai/jukebox
Openai
Jukebox
We’re introducing Jukebox, a neural net that generates music, including rudimentary singing, as raw audio in a variety of genres and artist styles. We’re releasing the model weights and code, along with a tool to explore the generated samples.
Measuring Information Propagation in Literary Social Network
Annotated dataset of 100 works of fiction to support tasks in natural language processing and the computational humanities.
Code: https://github.com/dbamman/litbank
Paper: https://arxiv.org/pdf/2004.13980v1.pdf
Annotated dataset of 100 works of fiction to support tasks in natural language processing and the computational humanities.
Code: https://github.com/dbamman/litbank
Paper: https://arxiv.org/pdf/2004.13980v1.pdf
📈 Learning Convolutional Neural Networks with Interactive Visualization
Interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture.
Video: https://www.youtube.com/watch?v=HnWIHWFbuUQ&feature=youtu.be
Demo: https://poloclub.github.io/cnn-explainer/
Github: https://github.com/poloclub/cnn-explainer
Paper: https://arxiv.org/abs/2004.15004v1
Interactive visualization tool designed for non-experts to learn and examine convolutional neural networks (CNNs), a foundational deep learning model architecture.
Video: https://www.youtube.com/watch?v=HnWIHWFbuUQ&feature=youtu.be
Demo: https://poloclub.github.io/cnn-explainer/
Github: https://github.com/poloclub/cnn-explainer
Paper: https://arxiv.org/abs/2004.15004v1
YouTube
Demo Video "CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization"
This is a demo video for the manuscript: "CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualization"
For a live demo, visit: https://poloclub.github.io/cnn-explainer/
Music: Carefree by Kevin MacLeod
Link: https://filmmusic.io/song/3476…
For a live demo, visit: https://poloclub.github.io/cnn-explainer/
Music: Carefree by Kevin MacLeod
Link: https://filmmusic.io/song/3476…
This media is not supported in your browser
VIEW IN TELEGRAM
NUBIA (NeUral Based Interchangeability Assessor) is a new SoTA evaluation metric for text generation
Methodology to build automatic evaluation metrics for text generation using only machine learning models as core components
https://wl-research.github.io/blog/
Github: https://github.com/wl-research/nubia
Paper: https://arxiv.org/abs/2004.14667v1
Colab: https://colab.research.google.com/drive/1_K8pOB8fRRnkBPwlcmvUNHgCr4ur8rFg
Methodology to build automatic evaluation metrics for text generation using only machine learning models as core components
https://wl-research.github.io/blog/
Github: https://github.com/wl-research/nubia
Paper: https://arxiv.org/abs/2004.14667v1
Colab: https://colab.research.google.com/drive/1_K8pOB8fRRnkBPwlcmvUNHgCr4ur8rFg
Why We Need DevOps for ML Data
https://tecton.ai/blog/devops-ml-data/
Хабр: https://habr.com/ru/company/itsumma/blog/500272/
https://tecton.ai/blog/devops-ml-data/
Хабр: https://habr.com/ru/company/itsumma/blog/500272/
👍1
This media is not supported in your browser
VIEW IN TELEGRAM
An Implementation of ERNIE For Language Understanding (including Pre-training models and Fine-tuning tools)
ERNIE 2.0 is a continual pre-training framework for language understanding in which pre-training tasks can be incrementally built and learned through multi-task learning.
ERNIE 2.0 from Baidu: https://github.com/PaddlePaddle/ERNIE
Dataset: https://gluebenchmark.com/tasks
Understanding Language using XLNet with autoregressive pre-training
https://medium.com/@zxiao2015/understanding-language-using-xlnet-with-autoregressive-pre-training-9c86e5bea443
ERNIE 2.0 is a continual pre-training framework for language understanding in which pre-training tasks can be incrementally built and learned through multi-task learning.
ERNIE 2.0 from Baidu: https://github.com/PaddlePaddle/ERNIE
Dataset: https://gluebenchmark.com/tasks
Understanding Language using XLNet with autoregressive pre-training
https://medium.com/@zxiao2015/understanding-language-using-xlnet-with-autoregressive-pre-training-9c86e5bea443
The Best Deep Learning Papers from the ICLR 2020 Conference
https://neptune.ai/blog/iclr-2020-deep-learning
https://neptune.ai/blog/iclr-2020-deep-learning
neptune.ai
Blog - neptune.ai
Blog for ML/AI practicioners with articles about LLMOps. You'll find here guides, tutorials, case studies, tools reviews, and more.
Beneath the Tip of the Iceberg: Current Challenges and New Directions in Sentiment Analysis Research
Awesome Sentiment Analysis papers: https://github.com/declare-lab/awesome-sentiment-analysis
Paper: https://arxiv.org/abs/2005.00357v1
Awesome Sentiment Analysis papers: https://github.com/declare-lab/awesome-sentiment-analysis
Paper: https://arxiv.org/abs/2005.00357v1
GitHub
GitHub - declare-lab/awesome-sentiment-analysis: Reading list for Awesome Sentiment Analysis papers
Reading list for Awesome Sentiment Analysis papers - declare-lab/awesome-sentiment-analysis
Global explanations for discovering bias in data
Github: https://github.com/agamiko/gebi
Code: https://github.com/AgaMiko/GEBI/blob/master/notebooks/GEBI.ipynb
Paper: https://arxiv.org/abs/2005.02269v1
Github: https://github.com/agamiko/gebi
Code: https://github.com/AgaMiko/GEBI/blob/master/notebooks/GEBI.ipynb
Paper: https://arxiv.org/abs/2005.02269v1
Set of Machine Learning Python plugins for GIMP
This paper introduces GIMP-ML, a set of Python plugins for the widely popular GNU Image Manipulation Program (GIMP). It enables the use of recent advances in computer vision to the conventional image editing pipeline.
Github: https://github.com/kritiksoman/GIMP-ML
Paper: https://arxiv.org/abs/2004.13060
Demo: https://www.youtube.com/watch?v=HVwISLRow_0
This paper introduces GIMP-ML, a set of Python plugins for the widely popular GNU Image Manipulation Program (GIMP). It enables the use of recent advances in computer vision to the conventional image editing pipeline.
Github: https://github.com/kritiksoman/GIMP-ML
Paper: https://arxiv.org/abs/2004.13060
Demo: https://www.youtube.com/watch?v=HVwISLRow_0
TK & TKL - Efficient Transformer-based neural re-ranking models
TK employs a small number of low-dimensional Transformer layers to contextualize query and document word embeddings. TK scores the interactions of the contextualized representations with simple, yet effective soft-histograms based on the kernel-pooling technique .
Github: https://github.com/sebastian-hofstaetter/transformer-kernel-ranking
Paper: https://arxiv.org/abs/2005.04908v1
The Neural-IR-Explorer is a interactive exploration tool. It allows you to browse around the actual results of a neural re-ranking run
https://neural-ir-explorer.ec.tuwien.ac.at/
TK employs a small number of low-dimensional Transformer layers to contextualize query and document word embeddings. TK scores the interactions of the contextualized representations with simple, yet effective soft-histograms based on the kernel-pooling technique .
Github: https://github.com/sebastian-hofstaetter/transformer-kernel-ranking
Paper: https://arxiv.org/abs/2005.04908v1
The Neural-IR-Explorer is a interactive exploration tool. It allows you to browse around the actual results of a neural re-ranking run
https://neural-ir-explorer.ec.tuwien.ac.at/
👍1
Fine-tuning ResNet with Keras, TensorFlow, and Deep Learning
In this tutorial, you will learn how to fine-tune ResNet using Keras, TensorFlow, and Deep Learning.
https://www.pyimagesearch.com/2020/04/27/fine-tuning-resnet-with-keras-tensorflow-and-deep-learning/
In this tutorial, you will learn how to fine-tune ResNet using Keras, TensorFlow, and Deep Learning.
https://www.pyimagesearch.com/2020/04/27/fine-tuning-resnet-with-keras-tensorflow-and-deep-learning/
Little Ball of Fur
Little Ball of Fur consists of methods to do sampling of graph structured data
Documentation : https://little-ball-of-fur.readthedocs.io/en/latest/#little-ball-of-fur-documentation
github: https://github.com/benedekrozemberczki/littleballoffur
paper: https://arxiv.org/abs/2005.05257v1
Little Ball of Fur consists of methods to do sampling of graph structured data
Documentation : https://little-ball-of-fur.readthedocs.io/en/latest/#little-ball-of-fur-documentation
github: https://github.com/benedekrozemberczki/littleballoffur
paper: https://arxiv.org/abs/2005.05257v1
GitHub
GitHub - benedekrozemberczki/littleballoffur: Little Ball of Fur - A graph sampling extension library for NetworKit and NetworkX…
Little Ball of Fur - A graph sampling extension library for NetworKit and NetworkX (CIKM 2020) - benedekrozemberczki/littleballoffur
1008 machine translation models, covering of 140 different languages
https://huggingface.co/models?search=Helsinki-NLP%2Fopus-mt
https://huggingface.co/models?search=Helsinki-NLP%2Fopus-mt
huggingface.co
Models - Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
FlowTron: Improved Text to Speech Engine from NVIDIA
Paper: https://arxiv.org/abs/2005.05957
Code: https://github.com/NVIDIA/flowtron
Paper: https://arxiv.org/abs/2005.05957
Code: https://github.com/NVIDIA/flowtron
GitHub
GitHub - NVIDIA/flowtron: Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control…
Flowtron is an auto-regressive flow-based generative network for text to speech synthesis with control over speech variation and style transfer - NVIDIA/flowtron
PyTorch version of Stable Baselines, improved implementations of reinforcement learning algorithms.
https://towardsdatascience.com/stable-baselines-a-fork-of-openai-baselines-reinforcement-learning-made-easy-df87c4b2fc82
Documentation: https://stable-baselines3.readthedocs.io
Githab: https://github.com/DLR-RM/stable-baselines3
Paper: https://arxiv.org/abs/2005.05719v1
https://towardsdatascience.com/stable-baselines-a-fork-of-openai-baselines-reinforcement-learning-made-easy-df87c4b2fc82
Documentation: https://stable-baselines3.readthedocs.io
Githab: https://github.com/DLR-RM/stable-baselines3
Paper: https://arxiv.org/abs/2005.05719v1
Medium
Stable Baselines: a Fork of OpenAI Baselines — Reinforcement Learning Made Easy
After several weeks of hard work, we are happy to announce the release of Stable Baselines, a set of implementations of Reinforcement Learning (RL) algorithms with a common interface, based on OpenAI…
An Ethical Application of Computer Vision and Deep Learning — Identifying Child Soldiers Through Automatic Age and Military Fatigue Detection
https://www.pyimagesearch.com/2020/05/11/an-ethical-application-of-computer-vision-and-deep-learning-identifying-child-soldiers-through-automatic-age-and-military-fatigue-detection/
https://www.pyimagesearch.com/2020/05/11/an-ethical-application-of-computer-vision-and-deep-learning-identifying-child-soldiers-through-automatic-age-and-military-fatigue-detection/
This media is not supported in your browser
VIEW IN TELEGRAM
Objects are the secret key to revealing the world between vision and language
https://www.microsoft.com/en-us/research/blog/objects-are-the-secret-key-to-revealing-the-world-between-vision-and-language/
https://www.microsoft.com/en-us/research/blog/objects-are-the-secret-key-to-revealing-the-world-between-vision-and-language/