KBpedia google
KBpedia is a comprehensive knowledge structure for promoting data interoperability and knowledge-based artificial intelligence, or KBAI. The KBpedia knowledge structure combines seven ‘core’ public knowledge bases – Wikipedia, Wikidata, schema.org, DBpedia, GeoNames, OpenCyc, and UMBEL – into an integrated whole. KBpedia’s upper structure, or knowledge graph, is the KBpedia Knowledge Ontology. We base KKO on the universal categories and knowledge representation theories of the great 19th century American logician, polymath and scientist, Charles Sanders Peirce. KBpedia, written primarily in OWL 2, includes 55,000 reference concepts, about 30 million entities, and 5,000 relations and properties, all organized according to about 70 modular typologies that can be readily substituted or expanded. We test candidates added to KBpedia using a rigorous (but still fallible) suite of logic and consistency tests – and best practices – before acceptance. The result is a flexible and computable knowledge graph that can be sliced-and-diced and configured for all sorts of machine learning tasks, including supervised, unsupervised and deep learning. …

Parallel Monte Carlo Graph Search (P-MCGS) google
Recently, there have been great interests in Monte Carlo Tree Search (MCTS) in AI research. Although the sequential version of MCTS has been studied widely, its parallel counterpart still lacks systematic study. This leads us to the following questions: \emph{how to design efficient parallel MCTS (or more general cases) algorithms with rigorous theoretical guarantee? Is it possible to achieve linear speedup?} In this paper, we consider the search problem on a more general acyclic one-root graph (namely, Monte Carlo Graph Search (MCGS)), which generalizes MCTS. We develop a parallel algorithm (P-MCGS) to assign multiple workers to investigate appropriate leaf nodes simultaneously. Our analysis shows that P-MCGS algorithm achieves linear speedup and that the sample complexity is comparable to its sequential counterpart. …

AutoQB google
In this paper, we propose a hierarchical deep reinforcement learning (DRL)-based AutoML framework, AutoQB, to automatically explore the design space of channel-level network quantization and binarization for hardware-friendly deep learning on mobile devices. Compared to prior DDPG-based quantization techniques, on the various CNN models, AutoQB automatically achieves the same inference accuracy by $\sim79\%$ less computing overhead, or improves the inference accuracy by $\sim2\%$ with the same computing cost. …

Adaptive Computation Steps (ACS) google
In this paper, we present Adaptive Computation Steps (ACS) algorithm, which enables end-to-end speech recognition models to dynamically decide how many frames should be processed to predict a linguistic output. The ACS equipped model follows the classic encoder-decoder framework, while unlike the attention-based models, it produces alignments independently at the encoder side using the correlation between adjacent frames. Thus, predictions can be made as soon as sufficient inter-frame information is received, which makes the model applicable in online cases. We verify the ACS algorithm on an open-source Mandarin speech corpus AIShell-1, and it achieves a parity of 35.2% CER with the attention-based model in the online occasion. To fully demonstrate the advantage of ACS algorithm, offline experiments are conducted, in which our ACS model achieves 21.6% and 20.1% CERs with and without language model, both outperforming the attention-based counterpart. Index Terms: Adaptive Computation Steps, Encoder-Decoder Recurrent Neural Networks, End-to-End Training. …