Search Results for author:
Found 9 papers, 9 papers with code
Architecture-Preserving Provable Repair of Deep Neural Networks
The repair has the flexibility to modify multiple layers of the DNN, and runs in polynomial time.
Provable Repair of Deep Neural Networks
This has motivated a large number of techniques for finding unsafe behavior in DNNs.
SyReNN: A Tool for Analyzing Deep Neural Networks
Formally, DNNs are complicated vector-valued functions which come in a variety of sizes and applications.
Analogy-Making as a Core Primitive in the Software Engineering Toolbox
In this paper, we argue that analogy making should be seen as a core primitive in software engineering.
Memory-Efficient Fixpoint Computation
We prove that our technique is optimal (i. e., it results in minimum memory footprint) for Bourdoncle's iteration strategy while computing the same result.
Programming Languages
Abstract Neural Networks
We present a framework parameterized by the abstract domain and activation functions used in the DNN that can be used to construct a corresponding ANN.
Deterministic Parallel Fixpoint Computation
The de facto approach for computing the approximation of this fixpoint uses a sequential algorithm based on weak topological order (WTO).
Programming Languages
Computing Linear Restrictions of Neural Networks
A linear restriction of a function is the same function with its domain restricted to points on a given line.
A Symbolic Neural Network Representation and its Application to Understanding, Verifying, and Patching Networks
Analysis and manipulation of trained neural networks is a challenging and important problem.
