Neural networks are exerting burgeoning influence in emerging artificial intelligence applications at the micro-edge, such as sensing systems and image processing. As many of these systems are typically self-powered, their circuits are expected to be resilient and efficient in the presence of continuous power variations caused by the harvesters. In this paper, we propose a novel mixed-signal (i.e. analogue/digital) approach of designing a power-elastic perceptron using the principle of pulse width modulation (PWM). Fundamental to the design are a number of parallel inverters that transcode the input-weight pairs based on the principle of PWM duty cycle. Since PWM-based inverters are typically agnostic to amplitude and frequency variations, the perceptron shows a high degree of power elasticity and robustness under these variations. We show extensive design analysis in Cadence Analog Design Environment tool using a 3 × 3 perceptron circuit as a case study to demonstrate the resilience in the presence of parameric variations.

In this paper, Wireless Personal Area Network (IEEE 802.15.4) wireless channel utilization using Memsic (formerly Crossbow) IRIS Motes is measured and compared to ns2.34 simulation and theoretical models. Results show divergence between calculated, simulated and experimental results at higher throughput. Experimental results also highlight the limitations of the MoteWorks framework with regard to channel throughput measurements. A set of mitigation strategies is outlined to improve future research efforts aiming to characterize the validity of simulation models using the Memsic wireless sensor nodes.

Schematic tables are a new representation for conditionals. Roughly a cross between decision tables and data flowgraphs, they represent computation and decision-making orthogonally. They unify the full range of conditional constructs, from if statements through pattern matching to polymorphic predicate dispatch. Program logic is maintained in a declarative canonical form that enforces completeness and disjointness among choices. Schematic tables can beused either as a code specification/generation tool, or as a self-contained diagrammatic programming language. They give program logic the clarity of truth tables, and support high-level direct manipulation of that logic, avoiding much of the mental computation demanded by conventional conditionals.

Representing programs as text strings makes programming harder then it has to be. The source text of a program is far removed from its behavior. Bridging this conceptual gulf is what makes programming so inhumanly difficult -- we are not compilers. Subtext is a new medium in which the representation of a program is the same thing as its execution. Like a spreadsheet, a program is visible and alive, constantly executing even as it is edited. Program edits are coherent semantic transformations.The essence of this new medium is copying. Programs are constructed by copying and executed by copy flow: the projection of changes through copies. The simple idea of copying develops into a rich theory of higher-order continual copying of trees. Notably absent are symbolic names, the workhorse of textual notation, replaced by immediately-bound explicit relationships. Subtext unifies traditionally distinct programming tools and concepts, and enables some novel ones. Ancestral structures are a new primitive data type that combines the features of lists and records, along with unproblematic multiple inheritance. Adaptive conditionals use first-class program edits to dynamically adapt behavior.A prototype implementation shows promise, but calls for much further research. Subtext suggests that we can make programming radically easier, if we are willing to be radical.

Constraints in predicate or relational logic can be translated into boolean logic and solved with a SAT solver. For faster solving, it is common to exploit the typing of predicates or relations, in order to reduce the number of boolean variables needed to encode the constraint. Here we show how to extend this idea to constraints expressed in a language with subtyping. Our technique, called atomization, refactors the type hierarchy into a flat collection of disjoint atomic types. The constraints are then decomposed into equivalent constraints involving smaller relations or predicates over these new types, which can then be solved in the normal fashion. Experiments with an implementation of this technique within the Alloy Analyzer show improved performance on practical software checking problems.

A type system for object models is described that supports subtyping, unions, and overloading of relation names. No special features need be added to the modelling language; in particular, there are no casts, and the meaning of an object model can be understood without mentioning types. A type error is associated with an expression that can be proved to be _irrelevant_, in the sense that it can be replaced by an empty set or relation without affecting the value of its enclosing constraint. Relevance is computed by a simple abstract interpretation.