Profile

Cover photo
Mat Kelcey
Works at Google
Lives in San Francisco Bay Area
356 followers|339,354 views
AboutPostsCollectionsPhotosVideos+1'sReviews

Stream

Mat Kelcey

Shared publicly  - 
 
We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely related to Holographic Reduced Representations and Long Short-Term Memory networks. Holographic Reduced Representations have limited capacity: as they store more information, each retrieval becomes noisier due to interference. Our system in contrast creates redundant copies of stored information, which enables retrieval with reduced noise. Experiments demonstrate faster learning on multiple memorization tasks.
Abstract: We investigate a new method to augment recurrent neural networks with extra memory without increasing the number of network parameters. The system has an associative memory based on complex-valued vectors and is closely related to Holographic Reduced Representations and Long Short-Term ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, network architecture and hyper-parameters, our algorithm robustly solves more than 20 simulated physics tasks, including classic problems such as cartpole swing-up, dexterous manipulation, legged locomotion and car driving. Our algorithm is able to find policies whose performance is competitive with those found by a planning algorithm with full access to the dynamics of the domain and its derivatives. We further demonstrate that for many of the tasks the algorithm can learn policies end-to-end: directly from raw pixel inputs.
Abstract: We adapt the ideas underlying the success of Deep Q-Learning to the continuous action domain. We present an actor-critic, model-free algorithm based on the deterministic policy gradient that can operate over continuous action spaces. Using the same learning algorithm, ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all these questions affirmatively. In particular, we first show that the recent DQN algorithm, which combines Q-learning with a deep neural network, suffers from substantial overestimations in some games in the Atari 2600 domain. We then show that the idea behind the Double Q-learning algorithm, which was introduced in a tabular setting, can be generalized to work with large-scale function approximation. We propose a specific adaptation to the DQN algorithm and show that the resulting algorithm not only reduces the observed overestimations, as hypothesized, but that this also leads to much better performance on several games.
Abstract: The popular Q-learning algorithm is known to overestimate action values under certain conditions. It was not previously known whether, in practice, such overestimations are common, whether they harm performance, and whether they can generally be prevented. In this paper, we answer all ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
Embedding Methods for NLP : EMNLP 2014 tutorial
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
We introduce a novel schema for sequence to sequence learning with a Deep Q-Network (DQN), which decodes the output sequence iteratively. The aim here is to enable the decoder to first tackle easier portions of the sequences, and then turn to cope with difficult parts. Specifically, in each iteration, an encoder-decoder Long Short-Term Memory (LSTM) network is employed to, from the input sequence, automatically create features to represent the internal states of and formulate a list of potential actions for the DQN. Take rephrasing a natural sentence as an example. This list can contain ranked potential words. Next, the DQN learns to make decision on which action (e.g., word) will be selected from the list to modify the current decoded sequence. The newly modified output sequence is subsequently used as the input to the DQN for the next decoding iteration. In each iteration, we also bias the reinforcement learning's attention to explore sequence portions which are previously difficult to be decoded. For evaluation, the proposed strategy was trained to decode ten thousands natural sentences. Our experiments indicate that, when compared to a left-to-right greedy beam search LSTM decoder, the proposed method performed competitively well when decoding sentences from the training set, but significantly outperformed the baseline when decoding unseen sentences, in terms of BLEU score obtained.
Abstract: We introduce a novel schema for sequence to sequence learning with a Deep Q-Network (DQN), which decodes the output sequence iteratively. The aim here is to enable the decoder to first tackle easier portions of the sequences, and then turn to cope with difficult parts.
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
"Learning to Compose Neural Networks for Question Answering" We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with network-assembly parameters via reinforcement learning, with only (world, question, answer) triples as supervision. Our approach, which we term a dynamic neural model network, achieves state-of-the-art results on benchmark datasets in both visual and structured domains.
Abstract: We describe a question answering model that applies to both images and structured knowledge bases. The model uses natural language strings to automatically assemble neural networks from a collection of composable modules. Parameters for these modules are learned jointly with ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
"Character-level Convolutional Networks for Text Classification" (aka “Text Understanding from Scratch v2) This article offers an empirical exploration on the use of character-level convolutional networks (ConvNets) for text classification. We constructed several largescale datasets to show that character-level convolutional networks could achieve state-of-the-art or competitive results. Comparisons are offered against traditional models such as bag of words, n-grams and their TFIDF variants, and deep learning models such as word-based ConvNets and recurrent neural networks.
1
Add a comment...
In their circles
286 people
Have them in circles
356 people
Chris Balogh's profile photo
Emre Safak's profile photo
Colas Anita's profile photo
Brent Snook's profile photo
海龙信's profile photo
ilaria walker's profile photo
Shane Culpepper's profile photo
Matez 1890's profile photo
Timothy Lau's profile photo

Mat Kelcey

Shared publicly  - 
 
In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, long term structure of language. We perform an exhaustive study on techniques such as character Convolutional Neural Networks or Long-Short Term Memory, on the One Billion Word Benchmark. Our best single model significantly improves state-of-the-art perplexity from 51.3 down to 30.0 (whilst reducing the number of parameters by a factor of 20), while an ensemble of models sets a new record by improving perplexity from 41.0 down to 24.2. We also release these models for the NLP and ML community to study and improve upon.
Abstract: In this work we explore recent advances in Recurrent Neural Networks for large scale Language Modeling, a task central to language understanding. We extend current models to deal with two key challenges present in this task: corpora and vocabulary sizes, and complex, ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
We propose a goal-driven web navigation as a benchmark task for evaluating an agent with abilities to understand natural language and plan on partially observed environments. In this challenging task, an agent navigates through a web site, which is represented as a graph consisting of web pages as nodes and hyperlinks as directed edges, to find a web page in which a query appears. The agent is required to have sophisticated high-level reasoning based on natural languages and efficient sequential decision making capability to succeed. We release a software tool, called WebNav, that automatically transforms a website into this goal-driven web navigation task, and as an example, we make WikiNav, a dataset constructed from the English Wikipedia containing approximately 5 million articles and more than 12 million queries for training. We evaluate two different agents based on neural networks on the WikiNav and provide the human performance. Our results show the difficulty of the task for both humans and machines. With this benchmark, we expect faster progress in developing artificial agents with natural language understanding and planning skills.
Abstract: We propose a goal-driven web navigation as a benchmark task for evaluating an agent with abilities to understand natural language and plan on partially observed environments. In this challenging task, an agent navigates through a web site, which is represented as a graph consisting of ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally experienced, regardless of their significance. In this paper we develop a framework for prioritizing experience, so as to replay important transitions more frequently, and therefore learn more efficiently. We use prioritized experience replay in Deep Q-Networks (DQN), a reinforcement learning algorithm that achieved human-level performance across many Atari games. DQN with prioritized experience replay achieves a new state-of-the-art, outperforming DQN with uniform replay on 41 out of 49 games.
Abstract: Experience replay lets online reinforcement learning agents remember and reuse experiences from the past. In prior work, experience transitions were uniformly sampled from a replay memory. However, this approach simply replays transitions at the same frequency that they were originally ...
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
Vincent is very smart so you should watch this asap
 
My Deep Learning Course with Udacity is live!

Four lectures and corresponding TensorFlow notebooks to learn about deep nets, convnets, embeddings, RNNs, and all the tricks to make them work!

Very excited to finally share, this was a lot of fun to put together.
Our brand new Deep Learning Course, a collaboration between Google and Udacity, will have you learning and mastering these techniques!
6 comments on original post
1
Add a comment...

Mat Kelcey

Shared publicly  - 
 
"Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism" We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is shared across all language pairs. We train the proposed multi-way, multilingual model on ten language pairs from WMT'15 simultaneously and observe clear performance improvements over models trained on only one language pair. In particular, we observe that the proposed model significantly improves the translation quality of low-resource language pairs.
Abstract: We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a ...
1
Add a comment...
Mat's Collections
People
In their circles
286 people
Have them in circles
356 people
Chris Balogh's profile photo
Emre Safak's profile photo
Colas Anita's profile photo
Brent Snook's profile photo
海龙信's profile photo
ilaria walker's profile photo
Shane Culpepper's profile photo
Matez 1890's profile photo
Timothy Lau's profile photo
Work
Occupation
Software Engineer
Skills
Machine learning, natural language processing, information retrieval, distributed systems.
Employment
  • Google
    Software Engineer, present
  • Wavii
    Software Engineer
  • Amazon Web Services
    Software Engineer
  • Lonely Planet
    Software Engineer
  • Sensis
    Software Engineer
  • Distra
    Software Engineer
  • Nokia
    Software Engineer
  • Australian Stock Exchange
    Software Engineer
Basic Information
Gender
Decline to State
Story
Tagline
data nerd wannabe
Introduction
I work in the Machine Intelligence group at Google building as-large-as-I-can-get neural networks for knowledge extraction.
Places
Map of the places this user has livedMap of the places this user has livedMap of the places this user has lived
Currently
San Francisco Bay Area
Previously
seattle - melbourne - calgary - london - sydney - hobart
Links
Contributor to
Mat Kelcey's +1's are the things they like, agree with, or want to recommend.
Clive Barker - Google Play
market.android.com

Clive Barker is an English author, film director, video game designer and visual artist best known for his work in both fantasy and horror f

Aphex Twin - Music on Google Play
market.android.com

Richard David James, best known by his stage name Aphex Twin, is a British electronic musician and composer. He has been described by The Gu

Chess Tactics Pro (Puzzles)
market.android.com

Get better at chess with this large collection of chess puzzles for all levels !This tactic trainer lets you practice in 3 different modes :

Google Search
market.android.com

Google Search app for Android: The fastest, easiest way to find what you need on the web and on your device.* Quickly search the web and you

NetHack
market.android.com

This is an Android port of NetHack: a classic roguelike game originally released in 1987.Main features ------------- * User-friendly interfa

Improving Photo Search: A Step Across the Semantic Gap
googleresearch.blogspot.com

Posted by Chuck Rosenberg, Image Search Team Last month at Google I/O, we showed a major upgrade to the photos experience: you can now easil

Machine Learning - Stanford University
ml-class.org

A bold experiment in distributed education, "Machine Learning" will be offered free and online to students worldwide during the fa

Game Theory
www.game-theory-class.org

Game Theory is a free online class taught by Matthew Jackson and Yoav Shoham.

Probabilistic Graphical Models
www.pgm-class.org

Probabilistic Graphical Models is a free online class taught by Daphne Koller.

RStudio
rstudio.org

News. RStudio v0.94 Available (6/15/2011). RStudio v0.94 is now available. In this release we've made lots of enhancements based on the

Hadoop 0.20.205.0 API
hadoop.apache.org

Frame Alert. This document is designed to be viewed using the frames feature. If you see this message, you are using a non-frame-capable web

Shapecatcher.com: Unicode Character Recognition
shapecatcher.com

You need to find a specific Unicode Character? With Shapecatcher.com you can search through a database of characters by simply drawing your

Duncan & Sons Automotive Service Center
plus.google.com

Duncan & Sons Automotive Service Center hasn't shared anything on this page with you.

Natural Language Processing
www.nlp-class.org

Natural Language Processing is a free online class taught by Chris Manning and Dan Jurafsky.

name value description hadoop.tmp.dir /tmp/hadoop-${user.name} A ...
hadoop.apache.org

name, value, description. hadoop.tmp.dir, /tmp/hadoop-${user.name}, A base for other temporary directories. hadoop.native.lib, true, Should

Apache OpenNLP Developer Documentation
incubator.apache.org

Written and maintained by the Apache OpenNLP Development Community. Version 1.5.2-incubating. Copyright © , The Apache Software Foundation.

ggplot.
had.co.nz

ggplot. An implementation of the grammar of graphics in R. Check out the documentation for ggplot2 - the next generation. ggplot is an imple

ChainMapper (Hadoop 0.20.1 API)
hadoop.apache.org

public class ChainMapper; extends Object; implements Mapper. The ChainMapper class allows to use multiple Mapper classes within a single Map

Neural net language models - Scholarpedia
www.scholarpedia.org

A language model is a function, or an algorithm for learning such a function, that captures the salient statistical characteristics of the d

tech stuff by mat kelcey
www.matpalm.com

my nerd blog. latent semantic analysis via the singular value decomposition (for dummies). semi supervised naive bayes. statistical synonyms

Great accidental find early one morning, just what I needed.
Public - 2 months ago
reviewed 2 months ago
Public - 2 years ago
reviewed 2 years ago
2 reviews
Map
Map
Map