Semantic segmentation is a challenging vision problem that usually necessitates the collection of large amounts of finely annotated data, which is often quite expensive to obtain. Coarsely annotated data provides an interesting alternative as it is usually substantially more cheap. In this work, we present a method to leverage coarsely annotated data along with fine supervision to produce better segmentation results than would be obtained when training using only the fine data. We validate our approach by simulating a scarce data setting with less than 200 low resolution images from the Cityscapes dataset and show that our method substantially outperforms solely training on the fine annotation data by an average of 15.52% mIoU and outperforms the coarse mask by an average of 5.28% mIoU.

We introduce a novel class of adjustment rules for a collection of beliefs. This is an extension of Lewis' imaging to absorb probabilistic evidence in generalized settings. Unlike standard tools for belief revision, our proposal may be used when information is inconsistent with an agent's belief base. We show that the functionals we introduce are based on the imaginary counterpart of probability kinematics for standard belief revision, and prove that, under certain conditions, all standard postulates for belief revision are satisfied.

With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query the model with their data via an API. However, if the user's input is sensitive, sending it to the server is not an option. Equally, the service provider does not want to share the model by sending it to the client for protecting its intellectual property and pay-per-query business model. In this paper, we propose MLCapsule, a guarded offline deployment of machine learning as a service. MLCapsule executes the machine learning model locally on the user's client and therefore the data never leaves the client. Meanwhile, MLCapsule offers the service provider the same level of control and security of its model as the commonly used server-side execution. In addition, MLCapsule is applicable to offline applications that require local execution. Beyond protecting against direct model access, we demonstrate that MLCapsule allows for implementing defenses against advanced attacks on machine learning models such as model stealing/reverse engineering and membership inference.

The most enigmatic aspect of consciousness is the fact that it is felt, as a subjective sensation. This particular aspect is explained by the theory proposed here. The theory encompasses both the computation that is presumably involved and the way in which that computation may be realized in the brain's neurobiology. It is assumed that the brain makes an internal estimate of an individual's own evolutionary fitness, which can be shown to produce an irreducible, distinct cause. Communicating components of the fitness estimate (either for external or internal use) requires inverting them. Such inversion can be performed by the thalamocortical feedback loop in the mammalian brain, if that loop is operating in a switched, dual-stage mode. A first (nonconscious) stage produces forward estimates, whereas the second (conscious) stage inverts those estimates. It is argued that inversion produces irreducible, distinct, and spatially localized causes, which are plausibly sensed as the feeling of consciousness.

The Decision Model and Notation (DMN) is a recent OMG standard for the elicitation and representation of decision models, and for managing their interconnection with business processes. DMN builds on the notion of decision table, and their combination into more complex decision requirements graphs (DRGs), which bridge between business process models and decision logic models. DRGs may rely on additional, external business knowledge models, whose functioning is not part of the standard. In this work, we consider one of the most important types of business knowledge, namely background knowledge that conceptually accounts for the structural aspects of the domain of interest, and propose decision requirement knowledge bases (DKBs), where DRGs are modeled in DMN, and domain knowledge is captured by means of first-order logic with datatypes. We provide a logic-based semantics for such an integration, and formalize different DMN reasoning tasks for DKBs. We then consider background knowledge formulated as a description logic ontology with datatypes, and show how the main verification tasks for DMN in this enriched setting, can be formalized as standard DL reasoning services, and actually carried out in ExpTime. We discuss the effectiveness of our framework on a case study in maritime security. This work is under consideration for publication in Theory and Practice of Logic Programming (TPLP).

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand. The training is performed in a simulated environment in which we randomize many of the physical properties of the system like friction coefficients and an object's appearance. Our policies transfer to the physical robot despite being trained entirely in simulation. Our method does not rely on any human demonstrations, but many behaviors found in human manipulation emerge naturally, including finger gaiting, multi-finger coordination, and the controlled use of gravity. Our results were obtained using the same distributed RL system that was used to train OpenAI Five. We also include a video of our results: https://youtu.be/jwSbzNHGflM

Attention mechanisms in biological perception are thought to select subsets of perceptual information for more sophisticated processing which would be prohibitive to perform on all sensory inputs. In computer vision, however, there has been relatively little exploration of hard attention, where some information is selectively ignored, in spite of the success of soft attention, where information is re-weighted and aggregated, but never filtered out. Here, we introduce a new approach for hard attention and find it achieves very competitive performance on a recently-released visual question answering datasets, equalling and in some cases surpassing similar soft attention architectures while entirely ignoring some features. Even though the hard attention mechanism is thought to be non-differentiable, we found that the feature magnitudes correlate with semantic relevance, and provide a useful signal for our mechanism's attentional selection criterion. Because hard attention selects important features of the input information, it can also be more efficient than analogous soft attention mechanisms. This is especially important for recent approaches that use non-local pairwise operations, whereby computational and memory costs are quadratic in the size of the set of features.

Google is working on some nifty new features for Google Maps, including a short list of your favorite places, the possibility of a'virtual positioning system' and more. Assistant is coming to Google Maps in a big way, with a ton of new shortcuts, as well as the ability for the digital assistant to text your friend when you're on your way. Google is rolling out a tool called'Your Match', which uses machine learning to determine your location and interests, serving up targeted suggestions for new businesses opening up in your area and more.

The researcher who invented Viagra and a colleague at Cambridge University have become the latest to join the ranks of drug developers using artificial intelligence and attracting attention from venture capitalists. Cambridge, UK-based Healx said Thursday that it had raised $10 million in a Series A funding round, led by London-based venture capital firm Balderton Capital. Fellow British venture capital firm Amadeus Capital Partners and Jonathan Milner – founder of life sciences supplier Abcam – also participated. Cambridge Rare Diseases Network founder Tim Guilliams and David Brown – who invented Pfizer's erectile dysfunction drug, which is now available as a generic – are the founders of Healx. The company uses the HealNet database, which maps more than 1 billion disease, patient and drug interactions and was built and maintained using machine learning techniques.

QSAR, ADMET, ML), de novo molecular design methods, and multi-parameter optimisation is also highly desirable, will programme in Python and be familiar with Cheminfo libraries RDKit, Cactvs, Schrödinger, and data sources such as ChEMBL, SureChEMBL, and PubChem. BenevolentAI is applying artificial intelligence to develop new medicines for hard to treat diseases. It is the first fully integrated AI company with pharmaceutical discovery and clinical development capabilities. BenevolentAI's technology aims to reduce the cost, decrease failure rates and increasing the speed at which medicines are delivered to patients. BenevolentAI currently employs 165 people who work in an unrivaled, cross functional environment that incorporates leading edge data scientists, computer scientists, mathematicians and drug development R&D scientists working side by side. The company is headquartered in London with further offices in New York and Belgium. BenevolentAI's research facility is located in Babraham Science Park, Cambridge (UK). The company's AI technology is being used to develop treatments to unmet patients' needs across a wide range of diseases, including Motor Neuron Disease, Parkinson's Disease, Glioblastoma and Sarcopenia.