We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

Given e-commerce scenarios that user profiles are invisible, session-based recommendation is proposed to generate recommendation results from short sessions. Previous work only considers the user's sequential behavior in the current session, whereas the user's main purpose in the current session is not emphasized. In this paper, we propose a novel neural networks framework, i.e., Neural Attentive Recommendation Machine (NARM), to tackle this problem. Specifically, we explore a hybrid encoder with an attention mechanism to model the user's sequential behavior and capture the user's main purpose in the current session, which are combined as a unified session representation later. We then compute the recommendation scores for each candidate item with a bi-linear matching scheme based on this unified session representation. We train NARM by jointly learning the item and session representations as well as their matchings. We carried out extensive experiments on two benchmark datasets. Our experimental results show that NARM outperforms state-of-the-art baselines on both datasets. Furthermore, we also find that NARM achieves a significant improvement on long sessions, which demonstrates its advantages in modeling the user's sequential behavior and main purpose simultaneously.

Neural Attentive Session-based Recommendation

Modern Graph Theory

Methods and apparatus for inhibiting longitudinal expansion of a body portion of an endoscopic sheath during inflation of an inflatable member are disclosed. In one embodiment, a sheath assembly includes a body portion adapted to encapsulate a distal end of an insertion tube, and an inflatable member coupled to the body portion and adapted to be inflated radially outwardly from the body portion. The sheath assembly further includes an expansion-inhibiting mechanism coupled to at least one of the inflatable member and the body portion. The expansion-inhibiting mechanism advantageously inhibits a longitudinal expansion of the body portion during inflation of the inflatable member. The expansion-inhibiting mechanism may assume a variety of embodiments, including, for example, a non-compliant member, a longitudinally-stretched portion, a reinforcing spring member, a pressure relief device, or a suitable detent mechanism.

Endoscopic sheath assemblies having longitudinal expansion inhibiting mechanisms

A video endoscope system includes a reusable control cabinet and an endoscope that is connectable thereto. The endoscope may be used with a single patient and then disposed. The endoscope includes an illumination mechanism, an image sensor, and an elongate shaft having one or more lumens located therein. An articulation joint at the distal end of the endoscope allows the distal end to be oriented by the actuators in the control cabinet or actuators in a control handle of the endoscope. Fluidics, electrical, navigation, image, display and data entry controls are integrated into the system along with other accessories.

Articulation joint for video endoscope

Internet is speeding up and modifying the manner in which daily tasks such as online shopping, paying utility bills, watching new movies, communicating, etc., are accomplished. As an example, in older shopping methods, products were mass produced for a single market and audience but that approach is no longer viable. Markets based on long product and development cycles can no longer survive. To stay competitive, markets need to provide different products and services to different customers with different needs. The shift to online shopping has made it incumbent on producers and retailers to customize for customers' needs while providing more options than were possible before. This, however, poses a problem for customers who must now analyze every offering in order to determine what they actually need and will benefit from. To aid customers in this scenario, we discuss about common recommender systems techniques that have been employed and their associated trade-offs.

Recommender systems in e-commerce

An endoscope which is both flexible and easily cleaned having a pair of telescoping sections at its distal end one of which carries a camera and which are alternately actuated to provide movement through a body passageway by a Bowden type of cable. Such cable has an outer helical casing with an inner steel wire. Respectively attached to the two cylindrical sections are inflatable bladders which provide for the movement above which also are an integral part of the flexible sterilized sheath being held to the respective sections by O-rings.

Endoscope with stretchable flexible sheath covering

Over the past several decades the dramatic increase in the availability of computational resources, coupled with the maturation of machine learning, has profoundly impacted sensor technology. In this Perspective, we discuss computational sensing with a focus on intelligent sensor system design. By leveraging inverse design and machine learning techniques, data acquisition hardware can be fundamentally redesigned to ‘lock-in’ to the optimal sensing data with respect to a user-defined cost function or design constraint. We envision a new generation of computational sensing systems that reduce the data burden while also improving sensing capabilities, enabling low-cost and compact sensor implementations engineered through iterative analysis of data-driven sensing outcomes. We believe that the methodologies discussed in this Perspective will permeate the design phase of sensing hardware, and thereby will fundamentally change and challenge traditional, intuition-driven sensor and readout designs in favour of application-targeted and perhaps highly non-intuitive implementations. Such computational sensors enabled by machine learning can therefore foster new and widely distributed applications that will benefit from ‘big data’ analytics and the internet of things to create powerful sensing networks, impacting various fields, including for example, biomedical diagnostics, environmental sensing and global health, among others. Traditional sensing techniques apply computational analysis at the output of the sensor hardware to separate signal from noise. A new, more holistic and potentially more powerful approach proposed in this Perspective is designing intelligent sensor systems that ‘lock-in’ to optimal sensing of data, making use of machine leaning strategies.

/pdf/machine-learning-and-computation-enabled-intelligent-sensor-5ai5ajrkpw.pdf

Machine learning and computation-enabled intelligent sensor design

A transmission line analyzer for automatically identifying the severities and locations of multiple mismatches generates a ripple waveform which is digitally analyzed by a fast fourier transform method. Foreign and harmonic signals are rejected, and return loss at each mismatch accurately determined.

Transmission line analyzer for automatically identifying the severities and locations of multiple mismatches

A non-contact angular position sensor has juxtaposed transmit and receive disks with a coupler disk, carrying a conductive attenuating pattern interposed therebetween. A pattern of inductive coils, which completely encircle both the transmit and receive disks have their inductive coupling individually attenuated in accordance with the angular position of the symmetrical conductive pattern on the intermediate coupling disk. The transmit disk is driven by a signal source which when received and demodulated by the receive coils and summed together provides a unique sinusoidal signal whose phase is indicative of the angular position of the intermediate coupler. The conductive pattern on the coupler is designed to provide a linear output.

Asad M. Madni

Papers

Recommender systems in e-commerce

Endoscope with stretchable flexible sheath covering

Machine learning and computation-enabled intelligent sensor design

Transmission line analyzer for automatically identifying the severities and locations of multiple mismatches

Angular position sensor with inductive attenuating coupler