Programming and Training Rate-Independent Chemical Reaction Networks

Embedding computation in biochemical environments incompatible with traditional electronics is expected to have wide-ranging impact in synthetic biology, medicine, nanofabrication and other fields. Natural biochemical systems are typically modeled by chemical reaction networks (CRNs), and CRNs can be used as a specification language for synthetic chemical computation. In this paper, we identify a class of CRNs called non-competitive (NC) whose equilibria are absolutely robust to reaction rates and kinetic rate law, because their behavior is captured solely by their stoichiometric structure. Unlike prior work on rate-independent CRNs, checking non-competition and using it as a design criterion is easy and promises robust output. We also present a technique to program NC-CRNs using well-founded deep learning methods, showing a translation procedure from rectified linear unit (ReLU) neural networks to NC-CRNs. In the case of binary weight ReLU networks, our translation procedure is surprisingly tight in the sense that a single bimolecular reaction corresponds to a single ReLU node and vice versa. This compactness argues that neural networks may be a fitting paradigm for programming rate-independent chemical computation. As proof of principle, we demonstrate our scheme with numerical simulations of CRNs translated from neural networks trained on traditional machine learning datasets (IRIS and MNIST), as well as tasks better aligned with potential biological applications including virus detection and spatial pattern formation.

Deep Molecular Programming: A Natural Implementation of Binary-Weight ReLU Neural Networks

Embedding computation in molecular contexts incompatible with traditional electronics is expected to have wide ranging impact in synthetic biology, medicine, nanofabrication and other fields. A key remaining challenge lies in developing programming paradigms for molecular computation that are well-aligned with the underlying chemical hardware and do not attempt to shoehorn ill-fitting electronics paradigms. We discover a surprisingly tight connection between a popular class of neural networks (Binary-weight ReLU aka BinaryConnect) and a class of coupled chemical reactions that are absolutely robust to reaction rates. The robustness of rate-independent chemical computation makes it a promising target for bioengineering implementation. We show how a BinaryConnect neural network trained in silico using well-founded deep learning optimization techniques, can be compiled to an equivalent chemical reaction network, providing a novel molecular programming paradigm. We illustrate such translation on the paradigmatic IRIS and MNIST datasets. Toward intended applications of chemical computation, we further use our method to generate a CRN that can discriminate between different virus types based on gene expression levels. Our work sets the stage for rich knowledge transfer between neural network and molecular programming communities.

A Study of the Learnability of Relational Properties

Relational properties, e.g., the connectivity structure of nodes in a distributed system, have many applications in software design and analysis. However, such properties often have to be written manually, which can be costly and error-prone. This paper introduces the MCML approach for empirically studying the learnability of a key class of such properties that can be expressed in the well-known software design language Alloy. A key novelty of MCML is quantification of the performance of and semantic differences among trained machine learning (ML) models, specifically decision trees, with respect to entire input spaces (up to a bound on the input size), and not just for given training and test datasets (as is the common practice). MCML reduces the quantification problems to the classic complexity theory problem of model counting, and employs state-of-the-art approximate and exact model counters for high efficiency. The results show that relatively simple ML models can achieve surprisingly high performance (accuracy and F1 score) at learning relational properties when evaluated in the common setting of using training and test datasets -- even when the training dataset is much smaller than the test dataset -- indicating the seeming simplicity of learning these properties. However, the use of MCML metrics based on model counting shows that the performance can degrade substantially when tested against the whole (bounded) input space, indicating the high complexity of precisely learning these properties, and the usefulness of model counting in quantifying the true accuracy.

MoËT: Interpretable and Verifiable Reinforcement Learning via Mixture of Expert Trees

Deep Reinforcement Learning (DRL) has led to many recent breakthroughs on complex control tasks, such as defeating the best human player in the game of Go. However, decisions made by the DRL agent are not explainable, hindering its applicability in safety-critical settings. Viper, a recently proposed technique, constructs a decision tree policy by mimicking the DRL agent. Decision trees are interpretable as each action made can be traced back to the decision rule path that lead to it. However, one global decision tree approximating the DRL policy has significant limitations with respect to the geometry of decision boundaries. We propose Mo\"ET, a more expressive, yet still interpretable model based on Mixture of Experts, consisting of a gating function that partitions the state space, and multiple decision tree experts that specialize on different partitions. We propose a training procedure to support non-differentiable decision tree experts and integrate it into imitation learning procedure of Viper. We evaluate our algorithm on four OpenAI gym environments, and show that the policy constructed in such a way is more performant and better mimics the DRL agent by lowering mispredictions and increasing the reward. We also show that Mo\"ET policies are amenable for verification using off-the-shelf automated theorem provers such as Z3.

Neural Program Repair by Jointly Learning to Localize and Repair

Due to its potential to improve programmer productivity and software quality, automated program repair has been an active topic of research. Newer techniques harness neural networks to learn directly from examples of buggy programs and their fixes. In this work, we consider a recently identified class of bugs called variable-misuse bugs. The state-of-the-art solution for variable misuse enumerates potential fixes for all possible bug locations in a program, before selecting the best prediction. We show that it is beneficial to train a model that jointly and directly localizes and repairs variable-misuse bugs. We present multi-headed pointer networks for this purpose, with one head each for localization and repair. The experimental results show that the joint model significantly outperforms an enumerative solution that uses a pointer based model for repair alone.