Neural Information Processing Systems http://nips.cc/

However, knowing which data to present during different stages of training is a challenging problem.

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1807" "Title:","Zero-shot recognition with unreliable attributes" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. The paper strives to bridge the gap between the theory and practice of attribute-based zero-shot learning. The theory is that novel classes can be recognized automatically using pre-trained attribute predictors; in practice, however, learning these attribute classifiers can be as difficult or even more so than learning the object classes themselves. Random forests are trained to predict unseen classes from attribute vectors, and the training procedure takes into account the reliability of the attribute detectors by propagating a validation set through each decision tree at training time. The authors show how the method can be extended to handle training with a few training examples of test categories.

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper introduces a system that creates a classifier at test time for a given test image using a set of training examples in a specific neighborhood of the test image. The authors method proposes how to identify the neighborhood with the most informative training examples for the given test image. The authors indicate that their method is well suited to fine-grained image classification tasks. The authors' key observation is that while training images that are nearest to the test image may be informative, the most informative set of training images must be found by estimating the informativeness of all members of a neighborhood set together. The main contribution of this paper is a method for estimating the most informative neighborhood set in an online fashion for each new test image.

"NIPS Neural Information Processing Systems 8-11th December 2014, Montreal, Canada",,, "Paper ID:","1461" "Title:","The limits of squared Euclidean distance regularization" Current Reviews First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper considers the problem of empirical risk minimization with squared distance regularization, which results in a weight vector that is a linear combination of the training examples. The authors prove a linear lower bound on the average square loss of the algorithm on random problems, provided the loss function is nice enough, while the same problem is easy to learn by another algorithm. This is a well-written paper on a simple idea and result, with a rather interesting interpretation. The proposed conjectures on random features and neural networks should be fleshed out in more detail, or at least with more empirical evidence.

In many situations we have some measurement of confidence on "positiveness" for a binary label. The "positiveness" is a continuous value whose range is a bounded interval.

Neural Information Processing Systems http://nips.cc/

First provide a summary of the paper, and then address the following criteria: Quality, clarity, originality and significance. This paper proposes a new regularization method for structured prediction. The idea is relatively straightforward: a linear chain model is segmented into smaller subchains, each of which is added as an independent training example. Theorems are provided (with proofs in the supplement) showing how this regularization can reduce generalization risk and accelerate convergence rates. Empirical comparisons with state of the art approaches suggest that the resulting method is both faster and more accurate.

Neural Information Processing Systems http://nips.cc/

We identify the marginal polytope, the output space's convex hull,