Abstract
Contrarily to most conventional programming languages where certain symbols are used so as to create non-ambiguous grammars, most recent programming languages allow ambiguity. These ambiguities are solved using disambiguation rules, which dictate how the software that parses these languages should behave when faced with ambiguities. Such rules are highly efficient but come with some limitations - they cannot be further modified, their behaviour is hidden, and changing them implies re-building a parser. We propose a different approach for disambiguation. A set of disambiguation filters (expressed as combinators) are provided, and disambiguation can be achieved by composing combinators. New combinators can be created and, by having the disambiguation step separated from the parsing step, disambiguation rules can be changed without modifying the parser.

Abstract
Protocols for password authenticated key exchange (PAKE) allow two parties who share only a weak password to agree on a crypto-graphic key. We revisit the notion of PAKE in the universal composability (UC) framework, and propose a relaxation of the PAKE functionality of Canetti et al. that we call lazy-extraction PAKE (lePAKE). Our relaxation allows the ideal-world adversary to postpone its password guess until after a session is complete. We argue that this relaxed notion still provides meaningful security in the password-only setting. As our main result, we show that several PAKE protocols that were previously only proven secure with respect to a "game-based" definition of security can be shown to UC-realize the lePAKE functionality in the random-oracle model. These include SPEKE, SPAKE2, and TBPEKE, the most efficient PAKE schemes currently known.

Abstract
Reinforcement learning is becoming a more relevant area of research, as it allows robotic agents to learn complex tasks with evaluative feedback. One of the most critical challenges in robotics is the simultaneous localization and mapping problem. We have built a reinforcement learning environment where we trained an agent to control a team of two robots, with the task of cooperatively mapping a common area. Our training process takes the robots' sensors data as input and outputs the control action for each robot. We verified that our agent performed well in a small test environment, with little training, indicating that our approach could be a good starting point for end-to-end reinforcement learning for cooperative mapping.

Abstract
A multifunctional router IC to be included in the nodes of a wearable body sensor network is described and evaluated. The router targets different application scenarios, especially those including tens of sensors, embedded into textile materials and with high data-rate communication demands. The router IC supports two different functionality sets, one for sensor nodes and another for the base node, both based on the same circuit module. The nodes are connected to each other by means of woven thick conductive yarns forming a mesh topology with the base node at the center. From the standpoint of the network, each sensor node is a four port router capable of handling packets from destination nodes to the base node, with sufficient redundant paths. The adopted hybrid circuit and packet switching scheme significantly improve network performance in terms of end-to-end delay, throughput and power consumption. The IC also implements a highly precise, sub-microsecond one-way time synchronization protocol which is used for time stamping the acquired data. The communication module was implemented in a 4-metal, 0.35 mu m CMOS technology. The maximum data rate of the system is 35 Mbps while supporting up to 250 sensors, which exceeds current BAN applications scenarios.

Abstract
A key to the generalization ability of Convolutional Neural Networks (CNNs) is the idea that patterns that appear in one region of the image have a high probability of appearing in other regions. This notion is also true for other spatial relationships, such as orientation. Motivated by the fact that in the early layers of CNNs distinct filters often encode for the same feature at different angles, we propose to incorporate the rotation equivariant prior in these models. In this work, different regularization strategies that capture the notion of approximate equivariance were designed and quantitatively evaluated in their ability to generate rotation-equivariant models and their effect on the model's capacity to generalize to unseen data. Some of these strategies consistently lead to higher test set accuracies when compared to a baseline model, on classification tasks. We conclude that the rotation equivariance prior should be adopted in the general setting when modeling visual data.

Abstract
We present a model of market hyper-segmentation, where a monopolist acquires within a short time all information about the preferences of consumers who purchase its vertically differentiated products. The firm offers a new price/quality schedule after each commitment period. Lower consumer types may have an incentive to delay their purchases until next period to obtain a better introductory offer. The monopolist counters this incentive by offering higher informational rents. Considering the dynamic game played by the monopolist and its customers, we find that there is always a Markov perfect equilibrium (MPE) in which the firm immediately sells the good to all customers, offering the Mussa-Rosen static equilibrium schedule to first time customers (and getting full commitment profits). However, if the commitment period between two offers is long enough, there is another MPE with gradual market expansion. Contrary to the Coasian result for a durable-good monopoly, we find that in both equilibria the profit of the monopolist increases (and the aggregate consumers surplus decreases) as the interval of commitment shrinks. The model yields policy implications for regulations on collection and storage of customers information.