We propose a temporal segmentation and procedure learning model for long untrimmed and unconstrained videos, e.g., videos from YouTube. The proposed model segments a video into segments that constitute a procedure and learns the underlying temporal dependency among the procedure segments. The output procedure segments can be applied for other tasks, such as video description generation or activ...

We describe a new learning procedure for networks that contain groups of nonlinear units arranged in a closed loop. The aim of the learning is to discover codes that allow the activity vectors in a "visible" group to be represented by activity vectors in a "hidden" group. One way to test whether a code is an accurate representation is to try to reconstruct the visible vector from the hidden vec...

Differential privacy is a cryptographically motivated definition of privacy which has gained considerable attention in the algorithms, machine-learning and datamining communities. While there has been an explosion of work on differentially private machine learning algorithms, a major barrier to achieving end-to-end differential privacy in practical machine learning applications is the lack of a...

Wireless Sensor Networks (WSNs) is one of the important areas in research center, causing major impact on technology improvement. In a Wireless Sensor Network, attacks are usually based on the signature in a centralized approach which detects the anomalies. In this paper the existing Extended Kalman Filter (EKF) mechanism that can be used to find the malicious node which sends the false informa...

We present a class of structure detection procedures (SDPs) that can extract the characteristic structures in an arbitrary population of images. An SDP adaptively augments the power of a novel, statistical, structure test to reject the null hypothesis that a randomly chosen image is devoid of structure. The core of the structure test consists of an orthonormal basis B of receptive fields that i...

We investigate methods for parameter learning from incomplete data that is not missing at random. Likelihood-based methods then require the optimization of a profile likelihood that takes all possible missingness mechanisms into account. Optimizing this profile likelihood poses two main difficulties: multiple (local) maxima, and its very high-dimensional parameter space. In this paper a new met...

In many cases the identification of systems by means of fuzzy rules is given by taking these rules from a predetermined set of possible ones. In this case, the correct description of the system is to be given by a finite set of rules each with an associated weight which assesses its correctness or accuracy. Here we present a method to learn this consistence level or weight by a neural network. ...

In recognizing a pattern, honeybees Apis mellifera, may focus either on its ventral frontal part, or on the whole frontal image. We asked whether the conditioning procedure used to train the bees to a pattern determines the recognition strategy employed. Bees were trained with the same patterns presented vertically on the back walls of a Y maze. Conditioning was either absolute, that is, bees s...

In this paper, we present an algorithm for minimizing the difference between two submodular functions using a variational framework which is based on (an extension of) the concave-convex procedure [17]. Because several commonly used metrics in machine learning, like mutual information and conditional mutual information, are submodular, the problem of minimizing the difference of two submodular ...

Hill climbing is used to maximize an information theoretic measure of the difference between the actual behavior of a unit and the behavior that would be predicted by a statistician who knew the first order statistics of the inputs but believed them to be independent. This causes the unit to detect higher order correlations among its inputs. Initial simulations are presented, and seem encouragi...