We employ so-called quantum kernel estimation to exploit complex dynamics of solid-state nuclear magnetic resonance for machine learning. propose map an input a feature space by input-dependent Hamiltonian evolution, and the is estimated interference evolution. Simple learning tasks, namely one-dimensional regression tasks two-dimensional classification are performed using proton spins which ex...

Most existing works on multi-task learning (MTL) assume the same input space for different tasks. In this paper, we address a general setting where different tasks have heterogeneous input spaces. This setting has a lot of potential applications, yet it poses new algorithmic challenges how can we link seemingly uncorrelated tasks to mutually boost their learning performance? Our key observation...

Tabletops offer great opportunities for information visualization and visual analytics. Users benefit from possibilities like collaborative analysis and direct touch interaction. Providing interaction techniques that support users in accomplishing tasks is especially important, since “interaction is the fuel for analytic discourse” [Thomas and Cook 2005]. Tasks frequently needed in visual analy...

Symbolic machine-learning classifiers are known to suffer from near-sightedness when performing sequence segmentation (chunking) tasks in natural language processing: without special architectural additions they are oblivious of the decisions they made earlier when making new ones. We introduce a new pointwise-prediction single-classifier method that predicts trigrams of class labels on the bas...

We consider the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, we concentrate on tasks that are amenable to the principle of divide and conquer, and study what are its implications in terms of learning. This principle creates a powerful induct...

SIMPSON, CLARENCE ADRIANO. A System for Generating DeviceSpecific Action Sequences. (Under the direction of Robert St. Amant) As computing devices become more varied and complex, it has been shown that it is useful, perhaps even essential, to begin describing elements of human-computer interaction in more abstract terms. Much of the literature has focused on specific cases of interaction involv...

We consider the learning of algorithmic tasks by mere observation of input-output pairs. Rather than studying this as a black-box discrete regression problem with no assumption whatsoever on the input-output mapping, we concentrate on tasks that are amenable to the principle of divide and conquer, and study what are its implications in terms of learning. This principle creates a powerful induct...

The GENDALC system has been previously used to evolve NN topologies for natural language tasks. This paper presents results on additional tasks that require remembering and processing of previous input patterns. These results indicate that GENDALC is particularly well suited for tasks that require remembering.