GoodAI

Prosek Point - Building A

Prosecká 851/64,

190 00

Prague, Czech Republic

  • Black Facebook Icon
  • Black Twitter Icon
  • Black YouTube Icon

Check out our sister company Keen Software House

Get in touch at info@goodai.com

GoodAI Bibliography

Overview

The present bibliography lists sources of interest from the viewpoint of GoodAI’s general AI research.

Our effort is informed by the following working assumptions:

  • Agents need the ability to grow their cognitive resources as they encounter progressively harder problems;

  • The growth of agents can be aided by human-designed curricula.

 

Most of the entries are recent papers of specific interest to this research direction. In addition, we include

  • Books and a few older papers with valuable background information;

  • Presentation slides and videos for some material not covered in papers.

 

The material is organized by research area:

  1. AI school: curricula and learning environments

  2. Machine learning topics: Growing architectures and more

  3. Cognitive architectures

  4. AI safety

AI school

This section contains material on curricula and learning environments.

 

Curriculum learning

Yoshua Bengio, Jérôme Louradour, Ronan Collobert, Jason Weston

2009/06

This paper introduces curriculum learning: learning accelerated by presenting easy examples first and progressively increasing the difficulty. The paper was a product of the BabyAI project. See also Bengio’s presentation on Deep Architectures for Baby AI.

Type: Very relevant

 

A Roadmap towards Machine Intelligence

Tomas Mikolov, Armand Joulin, Marco Baroni

2015/11

An interesting proposal for a language-based environment for raising intelligent agents.

Type: Very relevant

 

Artificial Tasks for Artificial Intelligence (video, slides)

Antoine Bordes, Jason Weston, Sumit Chopra, Tomas Mikolov, Armand Joulin, Léon Bottou

2015/05

On the shortcomings of present AI systems and how to learn for AGI.

Type: Very relevant

 

Cognitive development (book)

John H. Flavell, Patricia H. Miller, Scott A. Miller

This textbook describes the stages of human cognitive development.

2002

Type: Very relevant

 

Why Artificial Intelligence Needs a Task Theory

Kristinn R. Thórisson, Jordi Bieger, Thröstur Thorarensen, Jóna S. Sigurðardóttir, Bas R. Steunebrink

2016/07

An AI task theory, the authors argue, can give us more rigorous ways of comparing and evaluating intelligent behavior.

Type: Somewhat relevant

Machine learning

 

Growing architectures

Growing architectures learn new things while retaining existing knowledge.

 

Powerplay: Training an increasingly general problem solver by continually searching for the simplest still unsolvable problem

Jürgen Schmidhuber

2011

The author presents a framework for automatically discovering problems inspired by playful behavior in animals and humans.

Type: Very relevant

 

Progressive Neural Networks

Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell

2016/06

Progressive neural networks adapt to new tasks by growing new columns while retaining previously acquired knowledge.

Type: Very relevant

 

The Cascade-Correlation Learning Architecture

Scott Fahlman Christian, Christian Lebiere

1990

The Cascade-Correlation architecture accelerates learning by adding one hidden neuron at the time, keeping the preceding hidden weights frozen.

Type: Very relevant

 

Learning without Forgetting

Zhizhong Li, Derek Hoiem

2016/06

The authors present a method for adding capabilities to convolutional neural networks (CNNs) while retaining existing capabilities.

Type: Relevant

 

Growing Recursive Self-Improvers

Bas R. Steunebrink, Kristinn R. Thórisson, Jürgen Schmidhuber

2016/07

Introduces experience-based AI, a class of systems capable of continuous self-improvement.

Type: Somewhat relevant

 

Bounded Recursive Self-Improvement

Eric Nivel, Kristinn R. Thórisson, Bas R. Steunebrink, Haris Dindo, Giovanni Pezzulo, M. Rodriguez, C. Hernandez, Dimitri Ognibene, Jürgen Schmidhuber, Ricardo Sanz, Helgi Páll Helgason, Antonio Chella, Gudberg K. Jonsson

2013/12

The authors prototype “a machine that becomes increasingly better at behaving in underspecified circumstances, in a goal-directed way, on the job, by modeling itself and its environment as experience accumulates.”

Type: Somewhat relevant

Self-optimizing architectures

Determining the topology and hyperparameters for a model is labor intensive. The architectures described here learn their structure from the training data.

 

Online incremental feature learning with denoising autoencoders

Guanyu Zhou, Kihyuk Sohn, Honglak Lee

2012/04

This paper introduces an algorithm for learning features incrementally and determining the optimal model complexity from the data.

Type: Relevant

 

Convolutional Neural Fabrics

Shreyas Saxena, Jakob Verbeek

2016/06

Selecting the optimal convolutional network architecture for a given task remains an open problem. The authors propose a “neural fabric” that learns its structure from the data.

Type: Somewhat relevant

Deep architectures

 

Deep learning

Yann LeCun, Yoshua Bengio, Geoffrey Hinton

2015/04

A brief and readable overview of recent progress in deep learning.

Type: Very relevant

 

Deep learning in neural networks: An overview

Jürgen Schmidhuber

2015/01

A more comprehensive overview of deep learning.

Type: Very relevant

Extracting and Composing Robust Features with Denoising Autoencoders Pascal Vincent, Hugo Larochelle, Yoshua Bengio, Pierre-Antoine Manzagol

2008/08

Noise robust learning of Autoencoders.

Type: Relevant

Compositional learning

Compositional learning allows a learner to extends its abilities by recombining existing skills.

 

Learning to compose neural networks for question answering

Jacob Andreas, Marcus Rohrbach, Trevor Darrell, Dan Klein

2016/01

Learning how to compose (modules) neural networks to solve more complex tasks. One part of the algorithm learns how to do the composition of the modules and, in parallel, the specific modules are learned.

Type: Relevant

Transfer learning

This section provides some background on knowledge transfer between different learners.

 

A survey on transfer learning

Sinno Jialin Pan, Qiang Yang

2010/10

This paper provides a systematic overview of approaches to transfer learning.

TYPE: Very relevant

Sequence learning

This section discusses ways of learning temporal and other sequential patterns.

 

How the brain might work: A hierarchical and temporal model for learning and recognition (book)

Dileep George

2008/06

Presents a theory about bottom-up and top-down processing of information, the importance of both of those directions, the role of spatial and temporal patterns and how is it connected to neocortex.

Type: Very relevant

 

Temporal Pattern Processing

DeLiang Wang

2003

This paper provides an overview of approaches to the representation and processing of temporal patterns.

Type: Somewhat relevant

Program learning

By learning programs or algorithms an agent can represent and reuse procedural knowledge.

 

Neural Programmer-Interpreters

Scott Reed, Nando de Freitas

2016/02

Winner of best paper award at ICLR 2016. This paper uses strong supervision to train a large controller which is able to compose hard coded instructions into programs. The methodology is very general as multiple instruction sets are shown on a diverse array of tasks. And the approach generalises to larger task variants quite well.

Type: Very relevant

 

Neural Programmer: Inducing Latent Programs with Gradient Descent

Arving Neelakantan, Quoc V. Lee, Ilya Sutskever

2016/01

This paper uses weak supervision and gradient descent to train an agent to perform table lookups on data using a number of intrinsic operators. The agent is trained only with what the answer should be, so it tries to converge onto a sequence of instructions which satisfy the answer. If the NPI paper is for the architecture, this is for the method.

Type: Very relevant

 

Neural GPUs Learn Algorithms

Łukasz Kaiser, Ilya Sutskever

2016/03

Instead of creating deep models, this model is designed to be wide. It is based on the convolution-gated recurrent units and is able to do e.g. addition or multiplication. It can be trained on small examples and is able to generalize to long instances.

Type: Somewhat relevant

 

Programming with a Differentiable Forth Interpreter

Sebastian Riedel, Matko Bošnjak, Tim Rocktäschel

2016/05

The proposed system incorporates prior procedural knowledge as program sketches with slots that can be filled with learnable behaviour.

Type: Somewhat relevant

Spike-timing-dependent plasticity (STDP)

The papers presented here apply STDP to machine learning problems.

 

Learning dynamic Boltzmann machines with spike-timing dependent plasticity

Takayuki Osogami, Makoto Otsuka

2015/09

Unsupervised learning rule and temporal pattern representations for Boltzmann machines.           

Type: Very relevant           

Solving the distal reward problem through linkage of STDP and dopamine signaling                   

E. M. Izhikevich

2007/10

On the problem of delayed reward in biological and artificial neural networks.                        

Type: Somewhat relevant

Reinforcement learning

This section provides some papers describing recent progress in reinforcement learning.

 

Data-Efficient Learning of Feedback Policies from Image Pixels using Deep Dynamical Models

John-Alexander M. Assael, Niklas Wahlstrom, Thomas B. Schon, Marc Peter Deisenroth

2015/10

Principle of network composed of multiple parts, one for encoding the current state of the environment into more compressed representation. The other for predicting next state in this compressed state.

Type: Relevant

 

Tunable and Generic Problem Instance Generation for Multi-objective Reinforcement Learning

Garrett, Deon, Jordi Bieger, Kristinn R. Thórisson

2014/12

The paper introduces a tool to help researchers identify causes of failure and success of reinforce learning algorithms. The focus is primarily on multi-objective reinforcement learning.

Type: Somewhat relevant

 

Control of Memory, Active Perception, and Action in Minecraft

Junhyuk Oh, Valliappa Chockalingam, Satinder Singh, Honglak Lee

2016/05

How to use memory with DQN. It can remember where the stuff is placed in the environment, how to navigate there, and the designer can even visualized what it does.

Type: Somewhat relevant

Language

 

Representing Word Meaning and Order Information in a Composite Holographic Lexicon

Michael N. Jones, Douglas J. K. Mewhort

2007/01

Unsupervised extraction of meaning of words from text, which is based on holographic representations.

Type: Somewhat relevant

 

Distributed Representations of Sentences and Documents

Quoc V. Le, Tomas Mikolov

2014/06

The paper introduces the Paragraph Vector, an unsupervised framework that learns continuous distributed vector representations for variable-length texts.

Type: Somewhat relevant

Cognitive architectures

 

Thinking, Fast and Slow (book)

Daniel Kahneman

2011

High level point of view to the mind. What it does and why? How we solve some problems and what we decide to remember? The book provides summary (high-level) summary of the Mr. Kahneman work. The key point is that our mind consist of two major parts: lazy system that instantly decides what to do, and more accurate decision making part that carefully thinks about the next action. One system is is faster, another one slower. The book discuss how, and why, we choose between these two and how it affects us.

Type: Relevant

 

How to Build a Brain: A Neural Architecture for Biological Cognition (book)

Chris Eliasmith

2013

Description of heterogeneous modular engineered architecture, which combines holographic representations and spiking neural networks to produce biologically plausible information processing during solving selected cognitive tasks.

Type: Somewhat relevant

 

Cognitive Architectures and Autonomy: A Comparative Review

Kristinn R. Thórisson, Helgi Páll Helgasson

2012/06

Good review and comparison of some selected cognitive architecture designs.

Type: Relevant

 

How to Create a Mind (book)

Ray Kurzweil

2015/05

Overall discussion on the probable artificial mind architecture.

Type: Somewhat relevant

AI safety

 

Superintelligence: Paths, dangers, strategies (book)

Nick Bostrom

2014/07

An influential discussion of AI risks.

Type: Very relevant