Output range analysis for deep feedforward neural networks
Given a neural network (NN) and a set of possible inputs to the network described by polyhedral
constraints, we aim to compute a safe over-approximation of the set of possible output …
constraints, we aim to compute a safe over-approximation of the set of possible output …
Reachability analysis for neural feedback systems using regressive polynomial rule inference
We present an approach to construct reachable set overapproximations for continuous-time
dynamical systems controlled using neural network feedback systems. Feedforward deep …
dynamical systems controlled using neural network feedback systems. Feedforward deep …
Output range analysis for deep neural networks
Deep neural networks (NN) are extensively used for machine learning tasks such as image
classification, perception and control of autonomous systems. Increasingly, these deep NNs …
classification, perception and control of autonomous systems. Increasingly, these deep NNs …
Multi-objective optimization of �-EDM parameters for �-hole drilling on Hastelloy C 276 super alloy using response surface methodology and multi-objective genetic�…
Hastelloy C 276 is one of the nickel-based super alloys which has an excellent resistance
against corrosion at high temperature. It has a major application in nuclear and aerospace …
against corrosion at high temperature. It has a major application in nuclear and aerospace …
Learning and verification of feedback control systems using feedforward neural networks
We present an approach to learn and formally verify feedback laws for data-driven models
of neural networks. Neural networks are emerging as powerful and general data-driven …
of neural networks. Neural networks are emerging as powerful and general data-driven …
Multi-response optimisation of machining parameters to minimise the overcut and circularity error during micro-EDM of nickel-titanium shape memory alloy
Micro-electrical discharge machining (�-EDM) is one the most favourable process to machine
difficult to cut materials in micro-scale with higher accuracy and precision. In this paper, …
difficult to cut materials in micro-scale with higher accuracy and precision. In this paper, …
Sherlock-a tool for verification of neural network feedback systems: demo abstract
We present an approach for the synthesis and verification of neural network controllers for
closed loop dynamical systems, modelled as an ordinary differential equation. Feedforward …
closed loop dynamical systems, modelled as an ordinary differential equation. Feedforward …
Meso-level surface modification of Hastelloy C276 by WS2 powder mixed electrical discharge alloying process through micro-EDM setup
The present research provides a rigid, wear-resistant lubricating localized layer on Hastelloy
C276 (HC 276) surface at meso level by tungsten disulphide (WS 2 ) powder suspended …
C276 (HC 276) surface at meso level by tungsten disulphide (WS 2 ) powder suspended …
Interpretable detection of distribution shifts in learning enabled cyber-physical systems
The use of learning based components in cyber-physical systems (CPS) has created a gamut
of possible avenues to use high dimensional real world signals generated from sensors …
of possible avenues to use high dimensional real world signals generated from sensors …
Imprecise Bayesian neural networks
Uncertainty quantification and robustness to distribution shifts are important goals in machine
learning and artificial intelligence. Although Bayesian Neural Networks (BNNs) allow for …
learning and artificial intelligence. Although Bayesian Neural Networks (BNNs) allow for …