Juicy Data

2019-10-15 12:51:05 ​​ML Career Advice and Reading Papers

One hour Andrew Ng's CS230 Lecture on Deep learning has been summarised into concise 5 minutes and was written in a spirit to retain what was said and largely to look back and implement it.

Material will help to navigate a career in ML/DL and to learn how to read research papers.

CS 230 Lectures: http://cs230.stanford.edu/lecture/

Blogpost: http://bit.ly/35AWNy4
#beginner #dl #deeplearning #cs230 Открыть/Комментировать

2019-10-12 13:10:44 ​​Microsoft open sources SandDance, a visual data exploration tool

By using easy-to-understand views, SandDance helps you find insights about your data, which in turn help you tell stories supported by data, build cases based on evidence, test hypotheses, dig deeper into surface explanations, support decisions for purchases, or relate data into a wider, real world context.

Preview: https://sanddance.js.org/
Git: https://github.com/Microsoft/SandDance

Blogpost: http://bit.ly/31bWO7Y
#js #sandance #microsoft Открыть/Комментировать

2019-10-11 18:03:30 ​​PyTorch Mobile: Deployment on iOS and Android

Support (and corresponding packages) to deploy PyTorch models directly to mobile devices for inference was added with the latest PyTorch 1.3 release.

Overview: https://pytorch.org/mobile/home/

iOS: https://pytorch.org/mobile/ios/
Android: https://pytorch.org/mobile/android/

#pytorch #package #python #mobile Открыть/Комментировать

2019-10-09 09:44:05 ​​Image Deduplicator (imagededup)

imagededup is a Python package that simplifies the task of finding exact and near duplicates in an image collection making use of CNNs and different hashing algorithms.

Code: https://github.com/idealo/imagededup

Docs: https://idealo.github.io/imagededup/
#imagededup #cnn #hashing #lib #python Открыть/Комментировать

2019-10-08 15:47:25 ​​The Paths Perspective on Value Learning

New post on Distill on how Temporal Difference learning merges paths of experience for greater statistical efficiency.

Blogpost: https://distill.pub/2019/paths-perspective-on-value-learning/
#distill #research #rl #qlearning Открыть/Комментировать

2019-10-01 09:51:49 ​​TensorFlow 2.0.0 is out

TensorFlow 2.0 focuses on simplicity and ease of use, featuring updates like:

- Easy model building with Keras and eager execution;
- Robust model deployment in production on any platform;
- Powerful experimentation for research;
- API simplification by reducing duplication and removing deprecated endpoints.

TF2.0 Guide: https://www.tensorflow.org/guide/effective_tf2
Installation: https://www.tensorflow.org/install

BlogPost: https://telegra.ph/TensorFlow-20-is-now-available-10-01
#google #tf #tensorflow #tf2 Открыть/Комментировать

2019-09-12 10:28:10 ​​CTRL - A Conditional Transformer Language Model

CTRL is a 1.6 billion-parameter language model with powerful and controllable artificial text generation that can predict which subset of the training data most influenced a generated text sequence.

Paper: https://einstein.ai/presentations/ctrl.pdf
Code: https://github.com/salesforce/ctrl

BlogPost: http://bit.ly/2mesY47
#cntrl #nlp #ai #salesforce #transformer Открыть/Комментировать

2019-09-06 14:29:56 ​​STEGASURAS - Neural Steganography with GPT-2

Service based on EMNLP paper "Neural Linguistic Steganography", hiding secret messages in natural language via arithmetic coding and GPT-2. Using arithmetic coding in reverse enables extremely efficient steganography, and when combined with modern language models like GPT-2 it allows for convincing cover text generations that encode

Paper: https://arxiv.org/abs/1909.01496
Code: https://github.com/harvardnlp/NeuralSteganography

Demo: https://steganography.live
#gpt #gpt2 #ai #nlp #steganography Открыть/Комментировать

2019-09-04 16:22:50 ​​Neural Structured Learning in TensorFlow

TF introduces Neural Structured Learning (NSL) which is a new learning paradigm to train neural networks by leveraging structured signals in addition to feature inputs. Structure can be explicit as represented by a graph or implicit as induced by adversarial perturbation.

NSL Overview: http://bit.ly/2lYh3au
GitHub: http://bit.ly/2lDaLwx

BlogPost: https://telegra.ph/Neural-Structured-Learning-in-TensorFlow-09-04
#nsl #tf #tensorflow #ai Открыть/Комментировать

2019-09-03 17:24:54 ​​AI Cheatsheets

Cheatsheets for TensorFlow, PyTorch, Keras and other popular libraries in Presentations and PDF formats.

Service developers are also working to introduce an Interactive Shell/Python Console to write and execute the machine learning/deep learning code.

Git: https://github.com/kailashahirwar/cheatsheets-ai
Site: http://www.aicheatsheets.com/
#keras #pytorch #tf #cheatsheet Открыть/Комментировать