New method tackles reinforcement learning of complex ω-regular objectives without models.
problem Learning ω-regular objectives in unknown MDPs.
method Constructive reduction to almost-sure reachability, compilation to limit-deterministic Buechi automata.
result Optimal strategies computed from MDP observations using reinforcement learning.
Method trains policies for MDPs that satisfy LTL properties.
problem Training policies for MDPs that meet complex temporal logic constraints.
method Convert LTL to automaton, construct synchronised MDP, adapt reward function, apply neural Q-iteration.
result Synthesised policies satisfy specified LTL properties.
Train track automata for fully irreducible elements in Out(F_r).
problem Understanding fully irreducible elements in Out(F_r).
method Describing train track automata and geodesics in Outer Space.
result Geodesics in Culler-Vogtmann Outer Space for fully irreducible elements.
ADT uses adaptive sequences to improve automata learning.
problem Improving efficiency and accuracy of automata learning.
method Developed ADT algorithm with adaptive distinguishing sequences.
result ADT successfully integrated into LearnLib and used in research.
Study immersions of punctured 4-manifolds for quantum automata applications.
problem Existence of immersions between specific 4-manifolds.
method Analyzing immersions of punctured 4-manifolds to establish a partial order.
result Established a partial order on closed 4-manifolds via immersions.
Quantum cellular automata form a homology theory.
problem Understanding the topological structure of quantum cellular automata.
method Formal properties of coarse homology theories.
result Quantum cellular automata naturally form the degree-zero part of a coarse homology theory.
We obtain an index of the complexity of a random sequence by allowing the role of the measure in classical probability theory to be played by a function we call the generating mechanism. Typically, this generating mechanism will be a finite automata. We generate a set of biased sequences by applying a finite state auto…
Method extracts weighted automata from RNNs using state space regression.
problem Extracting weighted automata from RNNs for better model understanding.
method Regression on RNN state space to prioritize counterexample candidates.
result Quantitative/weighted extension of DFA extraction.
ISA learns subgoals for reinforcement learning agents.
problem Learning subgoals for efficient reinforcement learning.
method Induces a subgoal automaton from observation traces using inductive logic programming.
result ISA learns subgoals that improve RL performance and convergence.
Extracts weighted automata from black box models for sequential data.
problem Global interpretability of black box models for symbolic sequential data.
method Spectral algorithm for extracting weighted automata from black boxes without access to inner representation.
result Approximation of black box models using inferred weighted automata is of high quality.
We present an interactive version of an evidence-driven state-merging (EDSM) algorithm for learning variants of finite state automata. Learning these automata often amounts to recovering or reverse engineering the model generating the data despite noisy, incomplete, or imperfectly sampled data sources rather than optim…
Automaton models are often seen as interpretable models. Interpretability itself is not well defined: it remains unclear what interpretability means without first explicitly specifying objectives or desired attributes. In this paper, we identify the key properties used to interpret automata and propose a modification o…
Paper verifies RNNs using automata learning and model checking.
problem Verifying the correctness of RNNs is challenging.
method Learn a deterministic finite automaton from RNN, use model checking for verification.
result Can discover and generalize counterexamples to faulty flows.
Designs a Cellular Automata rule for forming touching loop patterns.
problem Forming stable touching loop patterns in a 2D grid.
method Developed a Cellular Automata rule that uses templates to cover the space and match patterns.
result The rule successfully evolves stable touching loop patterns in a 2D grid.
CURIE uses cellular automata to detect concept drift in data streams.
problem Detecting changes in data distribution (concept drift) in data streams.
method CURIE represents data stream distribution in a cellular automata grid and uses its neighborhood rule to detect changes.
result CURIE, when hybridized with base learners, performs competitively in detection metrics and classification accuracy.
Transformers simulate finite-state automata with fewer layers.
problem How do shallow, non-recurrent Transformers simulate complex computations?
method Hierarchical reparameterization of recurrent dynamics to simulate automata.
result Polynomial-sized, O(logT)-depth solutions exist and are common. Classifies knots in the Poincaré sphere, using fixed points and folding automata.
problem Classifying knots in the Poincaré sphere and understanding their properties.
method Theory of train tracks, folding automata, and knot Floer homology.
result Almost completely classified genus-two, hyperbolic, fibered knots.
DeepSynth synthesizes automata to guide deep RL agents through sparse, non-Markovian rewards.
problem Training deep RL agents with sparse, non-Markovian rewards and unknown high-level objectives.
method Employing a novel algorithm for synthesizing compact automata to uncover sequential structure from trace data.
result Reduces the number of iterations required for policy synthesis by two orders of magnitude and improves scalability.
A framework for analyzing financial systems under scenario constraints.
problem Quantifying worst-case and best-case performance in financial systems.
method Quantitative automata-based framework integrating event history automata and weighted finance finite automata.
result Exact calculation of upper and lower payoff bounds with interpretable witness event histories.
LUNAR uses cellular automata for real-time data classification in fast streams.
problem Real-time machine learning challenges with fast data streams and concept drift.
method Streamified cellular automata approach for incremental learning and adaptation.
result Competitive performance in classification compared to established online learning methods.
Algorithm extracts deterministic PDFA from probabilistic models with improved performance.
problem Learning deterministic models from probabilistic ones with noise.
method Adapted L* algorithm for probabilistic settings, using conditional probabilities and local tolerance.
result Achieves better performance on WER and NDCG than spectral extraction of WFAs.
We show how well known rules of back propagation arise from a weighted combination of finite automata. By redefining a finite automata as a predictor we combine the set of all k-state finite automata using a weighted majority algorithm. This aggregated prediction algorithm can be simplified using symmetry, and we pro…
The paper develops algorithms for computing in stochastic acceptors.
problem Computing input marginals and acceptance probabilities in stochastic acceptors.
method Dynamic programming for input marginals, EM for parameter estimation.
result Efficient algorithms for computing in stochastic acceptors.
New algorithm learns Markov decision processes from test data.
problem Learning Markov decision processes from limited test data.
method L*-based active learning with sampling.
result Sampling-based algorithm outperforms passive learning.
In the present work we introduce a stochastic cellular automata model in order to simulate the dynamics of the stock market. A direct percolation method is used to create a hierarchy of clusters of active traders on a two dimensional grid. Active traders are characterised by the decision to buy, (+1), or sell, (-1), a …
Combining automata learning and model-based testing generates sufficient training data for hybrid systems.
problem Challenges in constructing models of hybrid systems that combine physical and digital behavior.
method Exploits a combination of automata learning and model-based testing to generate sufficient training data.
result Recurrent neural networks trained with this data achieved significantly better results compared to models learned from random data.
State-regularized RNNs improve interpretability and performance on long-term memory tasks.
problem RNNs struggle with long-term memory and lack of interpretability.
method Introduce a stochastic state transition mechanism to limit state transitions to a finite set.
result State-regularized RNNs perform better on tasks requiring long-term memory.
In this paper, we unravel a fundamental connection between weighted finite automata~(WFAs) and second-order recurrent neural networks~(2-RNNs): in the case of sequences of discrete symbols, WFAs and 2-RNNs with linear activation functions are expressively equivalent. Motivated by this result, we build upon a recent ext…
Dual neural network architecture improves accuracy and interpretability.
problem Improving neural network interpretability and accuracy.
method Stacked recurrent and feedforward layers, binary activation function.
result Binary activation leads to simpler, more interpretable models with higher accuracy.
The paper presents an algorithm to determine discreteness of certain groups.
problem Determining discreteness of specific groups generated by parabolic transformations.
method Algorithmic approach based on historical mathematical paradigms.
result Equivalence of different approaches to the discreteness problem.
Reservoir computers and RNNs fall short of optimal prediction for stochastic PDFA.
problem Predicting stochastic processes generated by probabilistic deterministic finite-state automata.
method Generalized linear models, Reservoir computers, and Long Short-Term Memory (LSTM) RNNs were tested.
result Each method can fall short of maximal predictive accuracy by up to 50% after training.
Unified recurrent networks reveal differences in complexity levels of grammars.
problem Understanding the complexity and behavior of recurrent networks.
method Connecting recurrent networks with deterministic finite automata and formal grammars.
result Unified recurrent networks improve performance and match grammars from different complexity levels.
MBQC linked to CQCA, yielding efficient Ansätze.
problem Quantum computation efficiency and Ansatz adaptation.
method Relating MBQC to CQCA and constructing Ansätze.
result MBQC Ansätze can lead to different performances on learning tasks.
A new layer learns abstract relations from graph structure using finite-state automata.
problem Learning abstract relations from graph structure for program analysis.
method Relaxing the problem into learning finite-state automata policies on a graph-based POMDP and training these policies using implicit differentiation.
result GFSA layer finds shortcuts in grid-world graphs and reproduces simple static analyses on Python programs.
RL algorithm uses LTL to specify goals for MDPs, ensuring policy satisfaction.
problem Ensuring safety-critical RL policies meet specified goals formally.
method Formulates goals using LTL, translates to LDGBA, shapes synchronous reward function.
result Algorithm synthesizes policies satisfying LTL goals with maximal probability.
MPNPs use message passing to exploit relational structure in stochastic processes.
problem Lack of relational information in NPs limits their effectiveness in tasks with neighborhood rules.
method Introduce MPNPs that explicitly use relational structure through message passing.
result MPNPs outperform NPs in tasks with relational information, showing significant gains in few-shot learning.
Formal constraints improve RL safety in complex environments.
problem Safety constraints in reinforcement learning for complex environments.
method Specify constraints in formal languages, instantiate as finite automata, augment MDP states, learn dense cost function.
result Improved safety in training RL algorithms over various constraints.
This note gives a brief survey of the minimum dilatation problem for pseudo-Anosov mapping classes, and the first explicit train track description of an infinite family of pseudo-Anosov mapping classes with orientable stable foliations and the conjectural minimum dilatation for closed surfaces of even genus g≥2.
Recurrent neural networks trained on regular languages exhibit stable states that can recover from noise.
problem Stability of internal states in recurrent neural networks trained on regular languages.
method Empirical study with analysis of network activation and transitions between states.
result Recurrent neural networks trained on regular languages can recover from random perturbations and maintain stable states.
We introduce a new class of possibly noncompact n-dimensional manifolds without boundary associated to finite data which we call topological automata. This class is large enough to contain many interesting examples of open 2-dimensional and 3-dimensional manifolds of interest to low-dimensional topologists. Our main re…
Sparse regularization reduces NLP model complexity without sacrificing accuracy.
problem Excessive parameter usage in neural models for NLP leads to high memory and runtime usage.
method Apply group lasso to rational RNNs to learn sparse, parameter-efficient models.
result Sparse rational RNNs can have significantly fewer parameters than non-sparse models without losing performance.
Self-Organizing Maps provide quick flood predictions for real-time decision making.
problem Computational demand of physically-based overland flow models limits their use in real-time applications.
method Developed a flood-simulation specific SOM using cellular automata flood model results and synthetic DEM.
result SOMs can generate accurate water depth and flood extent results in a short time.
The paper distills a weighted automaton from RNNs for language modeling.
problem Tackles the gap between deep learning and grammatical inference.
method Uses a spectral approach to infer a weighted automaton from a trained RNN.
result Extracted weighted automata are good approximations of the RNNs, validating the approach.
We discuss here the mean-field theory for a cellular automata model of meta-learning. The meta-learning is the process of combining outcomes of individual learning procedures in order to determine the final decision with higher accuracy than any single learning method. Our method is constructed from an ensemble of inte…
Paper proves hardness of learning various complex models under local pseudorandom generators.
problem Hardness of learning various complex models.
method Existence of local pseudorandom generators.
result Proves hardness of learning shallow ReLU neural networks and other models.
Hidden tree Markov models allow learning distributions for tree structured data while being interpretable as nondeterministic automata. We provide a concise summary of the main approaches in literature, focusing in particular on the causality assumptions introduced by the choice of a specific tree visit direction. We w…
We investigate the problem of reliable communication between two legitimate parties over deletion channels under an active eavesdropping (aka jamming) adversarial model. To this goal, we develop a theoretical framework based on probabilistic finite-state automata to define novel encoding and decoding schemes that ensur…
We analyze deep neural networks in the large size and iteration limit, revealing a deterministic system of equations.
problem Understanding the behavior of deep neural networks in the asymptotic regime of large network sizes and iterations.
method Sequential limit of each hidden layer and characterization of parameter evolution, using weak convergence and stochastic analysis.
result The limit neural network recovers a global minimum with zero loss for the objective function.