3
3.0

Jun 29, 2018
06/18

by
Michael Bukatin; Steve Matthews

texts

######
eye 3

######
favorite 0

######
comment 0

We consider dataflow architecture for two classes of computations which admit taking linear combinations of execution runs: probabilistic sampling and generalized animation. We improve the earlier technique of almost continuous program transformations by adopting a discipline of bipartite graphs linking nodes obtained via general transformations and nodes obtained via linear transformations which makes it possible to develop and evolve dataflow programs over these classes of computations by...

Topics: Programming Languages, Computing Research Repository

Source: http://arxiv.org/abs/1601.01050

5
5.0

Jun 29, 2018
06/18

by
Michael Bukatin; Steve Matthews

texts

######
eye 5

######
favorite 0

######
comment 0

We consider two classes of stream-based computations which admit taking linear combinations of execution runs: probabilistic sampling and generalized animation. The dataflow architecture is a natural platform for programming with streams. The presence of linear combinations allows us to introduce the notion of almost continuous transformation of dataflow graphs. We introduce a new approach to higher-order dataflow programming: a dynamic dataflow program is a stream of dataflow graphs evolving...

Topics: Programming Languages, Computing Research Repository

Source: http://arxiv.org/abs/1601.00713

3
3.0

Jun 28, 2018
06/18

by
Michael Bukatin; Steve Matthews

texts

######
eye 3

######
favorite 0

######
comment 0

We consider two classes of computations which admit taking linear combinations of execution runs: probabilistic sampling and generalized animation. We argue that the task of program learning should be more tractable for these architectures than for conventional deterministic programs. We look at the recent advances in the "sampling the samplers" paradigm in higher-order probabilistic programming. We also discuss connections between partial inconsistency, non-monotonic inference, and...

Topics: Neural and Evolutionary Computing, Logic in Computer Science, Computing Research Repository

Source: http://arxiv.org/abs/1512.04639

3
3.0

Jun 29, 2018
06/18

by
Michael Bukatin; Steve Matthews; Andrey Radul

texts

######
eye 3

######
favorite 0

######
comment 0

Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of arbitrary linear streams, multiple types of powerful neurons, and allow to incorporate higher-order constructions. We expect them to be useful in machine learning and probabilistic programming, and in the synthesis of dynamic systems and of deterministic and probabilistic programs.

Topics: Neural and Evolutionary Computing, Computing Research Repository

Source: http://arxiv.org/abs/1603.09002

5
5.0

Jun 29, 2018
06/18

by
Michael Bukatin; Steve Matthews; Andrey Radul

texts

######
eye 5

######
favorite 0

######
comment 0

Dataflow matrix machines arise naturally in the context of synchronous dataflow programming with linear streams. They can be viewed as a rather powerful generalization of recurrent neural networks. Similarly to recurrent neural networks, large classes of dataflow matrix machines are described by matrices of numbers, and therefore dataflow matrix machines can be synthesized by computing their matrices. At the same time, the evidence is fairly strong that dataflow matrix machines have sufficient...

Topics: Programming Languages, Computing Research Repository, Neural and Evolutionary Computing

Source: http://arxiv.org/abs/1606.09470

5
5.0

Jun 29, 2018
06/18

by
Michael Bukatin; Steve Matthews; Andrey Radul

texts

######
eye 5

######
favorite 0

######
comment 0

Dataflow matrix machines are a powerful generalization of recurrent neural networks. They work with multiple types of linear streams and multiple types of neurons, including higher-order neurons which dynamically update the matrix describing weights and topology of the network in question while the network is running. It seems that the power of dataflow matrix machines is sufficient for them to be a convenient general purpose programming platform. This paper explores a number of useful...

Topics: Neural and Evolutionary Computing, Computing Research Repository, Programming Languages

Source: http://arxiv.org/abs/1605.05296

3
3.0

Jun 29, 2018
06/18

by
Michael Bukatin; Steve Matthews; Andrey Radul

texts

######
eye 3

######
favorite 0

######
comment 0

Dataflow matrix machines are self-referential generalized recurrent neural nets. The self-referential mechanism is provided via a stream of matrices defining the connectivity and weights of the network in question. A natural question is: what should play the role of untyped lambda-calculus for this programming architecture? The proposed answer is a discipline of programming with only one kind of streams, namely the streams of appropriately shaped matrices. This yields Pure Dataflow Matrix...

Topics: Programming Languages, Computing Research Repository

Source: http://arxiv.org/abs/1610.00831