84 citations · 228 across the 17 of their papers we have counts for
19 papers
Nondeterminism and Instability in Neural Network Optimization
Cecilia Summers, Michael J. Dinneen
Nondeterminism in neural network optimization produces uncertainty in performance, making small improvements difficult to discern from run-to-run variability. While uncertainty can…
Improved Adversarial Robustness via Logit Regularization Methods
Cecilia Summers, Michael J. Dinneen
While great progress has been made at making neural networks effective across a wide range of visual tasks, most models are surprisingly vulnerable. This frailness takes the form o…
Four Things Everyone Should Know to Improve Batch Normalization
Cecilia Summers, Michael J. Dinneen
A key component of most neural network architectures is the use of normalization layers, such as Batch Normalization. Despite its common use and large utility in optimizing deep ar…
A Hybrid Quantum-Classical Paradigm to Mitigate Embedding Costs in Quantum Annealing---Abridged Version
Alastair A. Abbott, Cristian S. Calude, Michael J. Dinneen +1
Quantum annealing has shown significant potential as an approach to near-term quantum computing. Despite promising progress towards obtaining a quantum speedup, quantum annealers a…
Experimentally Probing the Algorithmic Randomness and Incomputability of Quantum Randomness
Alastair A. Abbott, Cristian S. Calude, Michael J. Dinneen +1
The advantages of quantum random number generators (QRNGs) over pseudo-random number generators (PRNGs) are normally attributed to the nature of quantum measurements. This is often…
Improved Mixed-Example Data Augmentation
Cecilia Summers, Michael J. Dinneen
In order to reduce overfitting, neural networks are typically trained with data augmentation, the practice of artificially generating additional training data via label-preserving…
A Hybrid Quantum-Classical Paradigm to Mitigate Embedding Costs in Quantum Annealing
Alastair A. Abbott, Cristian S. Calude, Michael J. Dinneen +1
Despite rapid recent progress towards the development of quantum computers capable of providing computational advantages over classical computers, it seems likely that such compute…
An Efficient Algorithm for Mixed Domination on Generalized Series-Parallel Graphs
M. Rajaati, P. Sharifani, A. Shakiba +2
A mixed dominating set of a graph is a subset such that each element is adjacent or incident to at least one ele…
On fixed-parameter tractability of the mixed domination problem for graphs with bounded tree-width
M. Rajaati, M. R. Hooshmandasl, M. J. Dinneen +1
A mixed dominating set for a graph is a set such that every element is either adjacent or incident to an element o…
Edge- and Node-Disjoint Paths in P Systems
Michael J. Dinneen, Yun-Bum Kim, Radu Nicolescu
In this paper, we continue our development of algorithms used for topological network discovery. We present native P system versions of two fundamental problems in graph theory: fi…
Experimental Evidence of Quantum Randomness Incomputability
Cristian S. Calude, Michael J. Dinneen, Monica Dumitrescu +1
In contrast with software-generated randomness (called pseudo-randomness), quantum randomness is provable incomputable, i.e.\ it is not exactly reproducible by any algorithm. We pr…
How Random Is Quantum Randomness? An Experimental Approach
Cristian S. Calude, Michael J. Dinneen, Monica Dumitrescu +1
Our aim is to experimentally study the possibility of distinguishing between quantum sources of randomness--recently proved to be theoretically incomputable--and some well-known co…
New Solutions to the Firing Squad Synchronization Problems for Neural and Hyperdag P Systems
Michael J. Dinneen, Yun-Bum Kim, Radu Nicolescu
We propose two uniform solutions to an open question: the Firing Squad Synchronization Problem (FSSP), for hyperdag and symmetric neural P systems, with anonymous cells. Our soluti…
New results for the degree/diameter problem
Michael J. Dinneen, Paul R. Hafner
The results of computer searches for large graphs with given (small) degree and diameter are presented. The new graphs are Cayley graphs of semidirect products of cyclic groups and…
Algebraic constructions of efficient broadcast networks
Michael J. Dinneen, Vance Faber, Michael R. Fellows
Cayley graph techniques are introduced for the problem of constructing networks having the maximum possible number of nodes, among networks that satisfy prescribed bounds on the pa…
VLSI layouts and DNA physical mappings
Michael J. Dinneen
We show that an important problem (-ICG) in computational biology is equivalent to a colored version of a well-known graph layout problem (-CVS).
Obstructions to within a few vertices or edges of acyclic
Kevin Cattell, Michael J. Dinneen, Michael R. Fellows
Finite obstruction sets for lower ideals in the minor order are guaranteed to exist by the Graph Minor Theorem. It has been known for several years that, in principle, obstruction…
The complexity of broadcasting in bounded-degree networks
Michael J. Dinneen
Broadcasting concerns the dissemination of a message originating at one node of a network to all other nodes. This task is accomplished by placing a series of calls over the commun…
A simple linear-time algorithm for finding path-decompositions of small width
Kevin Cattell, Michael J. Dinneen, Michael R. Fellows
We described a simple algorithm running in linear time for each fixed constant , that either establishes that the pathwidth of a graph is greater than , or finds a path-d…