While deep neural networks have achieved state-of-the-art performance on many tasks across varied domains, they still remain black boxes whose inner workings are hard to interpret and understand. In this paper, we develop a novel method for efficiently capturing the behaviour of deep neural networks using kernels. In particular, we construct a hierarchy of increasingly complex kernels that enco...

The purpose of this article is to draw attention to current transgressions in scientific writing and to promote commitment to ethical standards and good science. All participants of any research project, particularly under interdiciplinary team approach, should not only play an active role on the management and carrying out of their study but also ensure that their study is not fraudulent. Manu...

The Gumbel trick is a method to sample from a discrete probability distribution, or to estimate its normalizing partition function. The method relies on repeatedly applying a random perturbation to the distribution in a particular way, each time solving for the most likely configuration. We derive an entire family of related methods, of which the Gumbel trick is one member, and show that the ne...

Monitoring and treating dormant tumors represents a major clinical challenge. We have recently found that early recurring tumors elicit an innate immune response that can be detected systemically. We also demonstrated that it may be possible to target minimal residual disease before or after immune evasion with carefully timed, rational therapeutic approaches.

In the process of proving some goal . . .Hi : Ti . . . ` C, we often need to invert an hypothesis Hi. More precisely, if its type Ti is an instance I(a) of an inductive type family I(x), we want to select the only possible constructors for I(a) and to get the corresponding components. Common instances of this situation occur when reasoning on language operational semantics given in small-step o...

there is a semi-proverbial expression in some persian literary texts that has not yet indexed in none of persian dictionaries –such as loqat-nameh or any other proverb references and has been totally neglected. accordingly it seems necessary being explained.  it has been mentioned under different topics such as ibn-e hâjib’s lamb, ibn-e hâjib’s sheep, ibn-e hâjib’s ewe in divans of adib-ol-mamâ...

We consider the tolerance of data structures to memory faults. We observe that many pointer-based data structures (e.g. linked lists, trees, etc.) are highly nonresilient to faults. A single fault in a linked list or tree may result in the loss of the entire set of data. In this paper we present a formal framework for studying the fault tolerance properties of pointer-based data structures, and...

Imperative programmers often use cyclically linked trees in order to achieve O(1) navigation time to neighbours. Some logic programmers believe that cyclic terms are necessary to achieve the same in logic-based languages. An old but little-known technique provides O(1) time and space navigation without cyclic links, in the form of reversible predicates. A small modification provides O(1) amorti...