Genre
Generating Accurate and Diverse Members of a Neural-Network Ensemble
Opitz, David W., Shavlik, Jude W.
In particular, combining separately trained neural networks (commonly referred to as a neural-network ensemble) has been demonstrated to be particularly successful (Alpaydin, 1993; Drucker et al., 1994; Hansen and Salamon, 1990; Hashem et al., 1994; Krogh and Vedelsby, 1995; Maclin and Shavlik, 1995; Perrone, 1992). Both theoretical (Hansen and Salamon, 1990; Krogh and Vedelsby, 1995) and empirical (Hashem et al., 1994; 536 D. W. OPITZ, J. W. SHA VLIK Maclin and Shavlik, 1995) work has shown that a good ensemble is one where the individual networks are both accurate and make their errors on different parts of the input space; however, most previous work has either focussed on combining the output of multiple trained networks or only indirectly addressed how we should generate a good set of networks.
The Capacity of a Bump
Recently, several researchers have reported encouraging experimental results when using Gaussian or bump-like activation functions in multilayer perceptrons. Networks of this type usually require fewer hidden layers and units and often learn much faster than typical sigmoidal networks. To explain these results we consider a hyper-ridge network, which is a simple perceptron with no hidden units and a ridยฅe activation function. If we are interested in partitioningp points in d dimensions into two classes then in the limit as d approaches infinity the capacity of a hyper-ridge and a perceptron is identical.
Using Unlabeled Data for Supervised Learning
For example, it is trivial to record hours of heartbeats from hundreds of patients. However, it is expensive to hire cardiologists to label each of the recorded beats. One response to the expense of class labels is to squeeze the most information possible out of each labeled example. Regularization and cross-validation both have this goal. A second response is to start with a small set of labeled examples and request labels of only those currently unlabeled examples that are expected to provide a significant improvement in the behavior of the classifier (Lewis & Catlett, 1994; Freund et al., 1993). A third response is to tap into a largely ignored potential source of information; namely, unlabeled examples. This response is supported by the theoretical work of Castelli and Cover (1995) which suggests that unlabeled examples have value in learning classification problems.
Is Learning The n-th Thing Any Easier Than Learning The First?
This paper investigates learning in a lifelong context. Lifelong learning addresses situations in which a learner faces a whole stream of learning tasks. Such scenarios provide the opportunity to transfer knowledge across multiple learning tasks, in order to generalize more accurately from less training data. In this paper, several different approaches to lifelong learning are described, and applied in an object recognition domain. It is shown that across the board, lifelong learning approaches generalize consistently more accurately from less training data, by their ability to transfer knowledge across learning tasks.
Prediction of Beta Sheets in Proteins
Krogh, Anders, Riis, Soren Kamaric
Most current methods for prediction of protein secondary structure use a small window of the protein sequence to predict the structure of the central amino acid. We describe a new method for prediction of the non-local structure called,8-sheet, which consists of two or more,8-strands that are connected by hydrogen bonds. Since,8-strands are often widely separated in the protein chain, a network with two windows is introduced. After training on a set of proteins the network predicts the sheets well, but there are many false positives. By using a global energy function the,8-sheet prediction is combined with a local prediction of the three secondary structures a-helix,,8-strand and coil.
Information through a Spiking Neuron
Stevens, Charles F., Zador, Anthony M.
While it is generally agreed that neurons transmit information about their synaptic inputs through spike trains, the code by which this information is transmitted is not well understood. An upper bound on the information encoded is obtained by hypothesizing that the precise timing of each spike conveys information. Here we develop a general approach to quantifying the information carried by spike trains under this hypothesis, and apply it to the leaky integrate-and-fire (IF) model of neuronal dynamics. We formulate the problem in terms of the probability distribution peT) of interspike intervals (ISIs), assuming that spikes are detected with arbitrary but finite temporal resolution. In the absence of added noise, all the variability in the ISIs could encode information, and the information rate is simply the entropy of the lSI distribution, H (T) (-p(T) log2 p(T)}, times the spike rate. H (T) thus provides an exact expression for the information rate. The methods developed here can be used to determine experimentally the information carried by spike trains, even when the lower bound of the information rate provided by the stimulus reconstruction method is not tight. In a preliminary series of experiments, we have used these methods to estimate information rates of hippocampal neurons in slice in response to somatic current injection. These pilot experiments suggest information rates as high as 6.3 bits/spike.
Using Pairs of Data-Points to Define Splits for Decision Trees
Hinton, Geoffrey E., Revow, Michael
CART either split the data using axis-aligned hyperplanes or they perform a computationally expensive search in the continuous space of hyperplanes with unrestricted orientations. We show that the limitations of the former can be overcome without resorting to the latter. For every pair of training data-points, there is one hyperplane that is orthogonal to the line joining the data-points and bisects this line. Such hyperplanes are plausible candidates for splits. In a comparison on a suite of 12 datasets we found that this method of generating candidate splits outperformed the standard methods, particularly when the training sets were small. 1 Introduction Binary decision trees come in many flavours, but they all rely on splitting the set of k-dimensional data-points at each internal node into two disjoint sets.
Adaptive Back-Propagation in On-Line Learning of Multilayer Networks
West, Ansgar H. L., Saad, David
This research has been motivated by the dominance of the suboptimal symmetric phase in online learning of two-layer feedforward networks trained by gradient descent [2]. This trapping is emphasized for inappropriate small learning rates but exists in all training scenarios, effecting the learning process considerably. We Adaptive Back-Propagation in Online Learning of Multilayer Networks 329 proposed an adaptive back-propagation training algorithm [Eq.
Classifying Facial Action
Bartlett, Marian Stewart, Viola, Paul A., Sejnowski, Terrence J., Golomb, Beatrice A., Larsen, Jan, Hager, Joseph C., Ekman, Paul
The Facial Action Coding System, (FACS), devised by Ekman and Friesen (1978), provides an objective meanS for measuring the facial muscle contractions involved in a facial expression. In this paper, we approach automated facial expression analysis by detecting and classifying facial actions. We generated a database of over 1100 image sequences of 24 subjects performing over 150 distinct facial actions or action combinations. We compare three different approaches to classifying the facial actions in these images: Holistic spatial analysis based on principal components of graylevel images; explicit measurement of local image features such as wrinkles; and template matching with motion flow fields. On a dataset containing six individual actions and 20 subjects, these methods had 89%, 57%, and 85% performances respectively for generalization to novel subjects. When combined, performance improved to 92%.