bookcold

533 Added | 1 Magazine | 140 Likes | 484 Followers | @bookcold | Keep up with bookcold on Flipboard, a place to see the stories, photos, and updates that matter to you. Flipboard creates a personalized magazine full of everything, from world news to life’s great moments. Download Flipboard for free and search for “bookcold”

Attention and Augmented Recurrent Neural Networks

A visual overview of neural attention, and the powerful extensions of neural networks being built on top of it.

Deep Learning

Salesforce research

Fully-parallel text generation for neural machine translation<p><b>Jiatao Gu and James Bradbury</b> - <i>November 07, 2017</i><p>Over the past few years, neural networks …

Deep Learning

Deep Learning’s Uncertainty Principle

DeepMind has a new paper where researchers have uncovered two “surpising findings”. The paper is described in “<b>Understanding Deep Learning through</b> …

Machine Learning

Lessons Learned Reproducing a Deep Reinforcement Learning Paper

There are a lot of neat things going on in deep reinforcement learning. One of the coolest things from last year was OpenAI and DeepMind’s work on …

Deep Learning

Monte Carlo Tree Search - beginners guide - Machine learning blog

Let’s try to describe the tic-tac-toe game tree you (partially) see:<p>at the very top, you can see the <b>root</b> of the tree, representing the <b>initial state</b> …

Algorithms

Understanding Deep Learning through Neuron Deletion

<b>Deep neural networks are composed of many individual neurons, which combine in complex and counterintuitive ways to solve a wide range of challenging</b> …

Variational autoencoders.

In my introductory post on autoencoders, I discussed various models (undercomplete, sparse, denoising, contractive) which take data as input and …

Deep Learning

Heuristics for Scientific Writing (a Machine Learning Perspective)

It’s January 28th and I should be working on my paper submissions. So should you! But why write and we can <b>meta-write</b>? ICML deadlines loom only twelve …

Common Patterns for Analyzing Data

Data is often messy, and a key step to building an accurate model is a thorough understanding of the data you're working with.<p>Before I started …

The Building Blocks of Interpretability

Interpretability techniques are normally studied in isolation. We explore the powerful interfaces that arise when you combine them -- and the rich …

Deep Learning

From GAN to WGAN

This post explains the maths behind a generative adversarial network (GAN) model and why it is hard to be trained. Wasserstein GAN is intended to …

Requests for Research

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2012). Imagenet classification with deep convolutional neural networks. In Advances in neural …

Natural Language Processing

Understanding Hinton’s Capsule Networks. Part I: Intuition.

Part of Understanding Hinton’s Capsule Networks Series:<p>Part I: Intuition (you are reading it now)<br>Part II: How Capsules Work<br>Part III: Dynamic Routing …

New Deep Learning Techniques (Schedule)

Programs<p>Long Programs<br>• Workshops<br>• Public Lectures<br>• Special Events and Conferences<br>• Student Research Programs<br>• Summer Schools<br>• Propose a …

Deep Reinforcement Learning Doesn't Work Yet

<i>This mostly cites papers from Berkeley, Google Brain, DeepMind, and OpenAI from the past few years, because that work is most visible to me. I’m</i> …

Taxonomy of Methods for Deep Meta Learning

Let’s talk about Meta-Learning because this is one confusing topic. I wrote a previous post about Deconstructing Meta-Learning which explored …

Deep Learning

Reinforcement Learning w/ Keras + OpenAI: Actor-Critic Models

<b>Quick Recap</b><p>Last time in our Keras/OpenAI tutorial, we discussed a very fundamental algorithm in reinforcement learning: the DQN. The Deep Q-Network …

Deep Learning

Machine Learning Top 10 Articles for the Past Month (v.Feb 2018)

For the past month<b>,</b> we ranked nearly 1,400 Machine Learning articles to pick the Top 10 stories that can help advance your career (0.7% …

Machine Learning

<b>Romain Paulus, Caiming Xiong and Richard Socher</b><p>The last few decades have witnessed a fundamental change in the challenge of taking in new …

Ideas on interpreting machine learning

You’ve probably heard by now that machine learning algorithms can use big data to predict whether a donor will give to a charity, whether an infant …

Machine Learning

6.S191 Introduction to Deep Learning

An introductory course on deep learning methods with applications to machine translation, image recognition, game playing, image generation and more. …

Machine Learning

The matrix calculus you need for deep learning

Introduce intermediate variables for nested subexpressions and subexpressions for both binary and unary operators; e.g., is binary, and other …

Deep Learning

30 Amazing Machine Learning Projects for the Past Year (v.2018)

<b>For the past year</b>, we’ve compared nearly 8,800 open source Machine Learning projects to pick Top 30 (0.3% chance).<p>This is an extremely competitive …

Machine Learning

10 Alarming Predictions for Deep Learning in 2018

I’ve got this ominous feeling that 2018 could be the year when everything just changes dramatically. The incredible breakthroughs we saw in 2017 for …

Deep Learning for Natural Language Processing (NLP): Advancements & Trends

Sentiment analysis in Twitter has drawn a lot of attention from researchers in NLP, but also in political and social sciences. That is why since …

Natural Language Processing

Lecture slides for STATS385, Fall 2017 | Theories of Deep Learning (STATS 385) by stats385

Machine Learning

AI and Deep Learning in 2017 – A Year in Review

The year is coming to an end. I did not write nearly as much as I had planned to. But I’m hoping to change that next year, with more tutorials around …

Machine Learning

Is AlphaZero really a scientific breakthrough in AI?

As you may probably know, DeepMind has recently published a paper on <b>AlphaZero</b> [1], a system that learns by itself and is able to master games like</b> …

AB - Introduction to Gaussian Processes - Part I

Gaussian processes may not be at the center of current machine learning hype but are still used at the forefront of research – they were recently …

Optimization for Deep Learning Highlights in 2017

Table of contents:• Improving Adam• Decoupling weight decay<br>• Fixing the exponential moving average<br>• Tuning the learning rate<br>• Warm restarts• SGD with …

Deep Learning