Imitation learning of sequential, goaldirected behavior by standard supervised techniques is often difficult. We frame learning such behaviors as a maximum margin structured prediction problem over a space of policies. In this approach, we learn mappings from features to cost so an optimal policy in an MDP with these cost mimics the expert’s behavior. Further, we demonstrate a simple, provably efficient approach to structured maximum margin learning, based on the subgradient method, that leverages existing fast algorithms for inference. Although the technique is general, it is particularly relevant in problems where A * and dynamic programming approaches make learning policies tractable in problems beyond the limitations of a QP formulation. We demonstrate our approach applied to route planning for outdoor mobile robots, where the behavior a designer wishes a planner to execute is often clear, while specifying cost functions that engender this behavior is a much more difficult task. 1.

We study the problem of classifying data in a given taxonomy when classifications associated with multiple and/or partial paths are allowed. We introduce a new algorithm that incrementally learns a linear-threshold classifier for each node of the taxonomy. A hierarchical classification is obtained by evaluating the trained node classifiers in a top-down fashion. To evaluate classifiers in our multipath framework, we define a new hierarchical loss function, the H-loss, capturing the intuition that whenever a classification mistake is made on a node of the taxonomy, then no loss should be charged for any additional mistake occurring in the subtree of that node. Making no assumptions on the mechanism generating the data instances, and assuming a linear noise model for the labels, we bound the H-loss of our on-line algorithm in terms of the H-loss of a reference classifier knowing the true parameters of the label-generating process. We show that, in expectation, the excess cumulative H-loss grows at most logarithmically in the length of the data sequence. Furthermore, our analysis reveals the precise dependence of the rate of convergence on the eigenstructure of the data each node observes. Our theoretical results are complemented by a number of experiments on texual corpora. In these experiments we show that, after only one epoch of training, our algorithm performs much better than Perceptron-based hierarchical classifiers, and reasonably close to a hierarchical support vector machine.

Kernel-based linear-threshold algorithms, such as support vector machines and Perceptron-like algorithms, are among the best available techniques for solving pattern classification problems. In this paper, we describe an extension of the classical Perceptron algorithm, called second-order Perceptron, and analyze its performance within the mistake bound model of on-line learning. The bound achieved by our algorithm depends on the sensitivity to second-order data information and is the best known mistake bound for (efficient) kernel-based linear-threshold classifiers to date. This mistake bound, which strictly generalizes the well-known Perceptron bound, is expressed in terms of the eigenvalues of the empirical data correlation matrix and depends on a parameter controlling the sensitivity of the algorithm to the distribution of these eigenvalues. Since the optimal setting of this parameter is not known a priori, we also analyze two variants of the second-order Perceptron algorithm: one that adaptively sets the value of the parameter in terms of the number of mistakes made so far, and one that is parameterless, based on pseudoinverses.

Programming robot behavior remains a challenging task. While it is often easy to abstractly define or even demonstrate a desired behavior, designing a controller that embodies the same behavior is difficult, time consuming, and ultimately expensive. The machine learning paradigm offers the promise of enabling “programming by demonstration ” for developing high-performance robotic systems. Unfortunately, many “behavioral cloning ” (Bain & Sammut, 1995; Pomerleau, 1989; LeCun et al., 2006) approaches that utilize classical tools of supervised learning (e.g. decision trees, neural networks, or support vector machines) do not fit the needs of modern robotic systems. These systems are often built atop sophisticated planning algorithms that efficiently reason far into the future; consequently, ignoring these planning algorithms in lieu of a supervised learning approach often leads to myopic and poor-quality robot performance. While planning algorithms have shown success in many real-world applications ranging from legged locomotion (Chestnutt et al., 2003) to outdoor unstructured navigation (Kelly et al., 2004; Stentz, 2009), such algorithms rely on fully specified cost functions that map sensor readings and environment models to quantifiable costs. Such cost functions are usually manually designed and programmed. Recently, a set of techniques has been developed that explore learning these functions from expert human demonstration.

We consider the task of tuning hyperparameters in SVM models based on minimizing a smooth performance validation function, e.g., smoothed k-fold crossvalidation error, using non-linear optimization techniques. The key computation in this approach is that of the gradient of the validation function with respect to hyperparameters. We show that for large-scale problems involving a wide choice of kernel-based models and validation functions, this computation can be very efficiently done; often within just a fraction of the training time. Empirical results show that a near-optimal set of hyperparameters can be identified by our approach with very few training rounds and gradient computations. 1

This thesis describes an effort to construct a scene understanding system that is able to analyze the content of real images. While constructing the system we had to provide solutions to many of the fundamental questions that every student of object recognition deals with daily. These include the choice of data set, the choice of success measurement, the representation of the image content, the selection of inference engine, and the representation of the relations between objects. The main test-bed for our system is the CBCL StreetScenes data base. It is a carefully labeled set of images, much larger than any similar data set available at the time it was collected. Each image in this data set was labeled for 9 common classes such as cars, pedestrians, roads and trees. Our system represents each image using a set of features that are based on a model of the human visual system constructed in our lab. We demonstrate that this biologically motivated image representation, along with its extensions, constitutes an effective representation for object detection, facilitating unprecedented levels of detection

Abstract. We study the problem of classifying data in a given taxonomy when classifications associated with multiple and/or partial paths are allowed. We introduce an incremental algorithm using a linear-threshold classifier at each node of the taxonomy. These classifiers are trained and evaluated in a hierarchical top-down fashion. We then define a hierachical and parametric data model and prove a bound on the probability that our algorithm guesses the wrong multilabel for a random instance compared to the same probability when the true model parameters are known. Our bound decreases exponentially with the number of training examples and depends in a detailed way on the interaction between the process parameters and the taxonomy structure. Preliminary experiments on real-world data provide support to our theoretical results. 1

minimization with randomization in learning

We describe a semi-supervised regression algorithm that learns to transform one time series into another time series given examples of the transformation. This algorithm is applied to tracking, where a time series of observations from sensors is transformed to a time series describing the pose of a target. Instead of defining and implementing such transformations for each tracking task separately, our algorithm learns a memoryless transformation of time series from a few example input-output mappings. The algorithm searches for a smooth function that fits the training examples and, when applied to the input time series, produces a time series that evolves according to assumed dynamics. The learning procedure is fast and lends itself to a closed-form solution. It is closely related to nonlinear system identification and manifold learning techniques. We demonstrate our algorithm on the tasks of tracking RFID tags from signal strength measurements, recovering the pose of rigid objects, deformable bodies, and articulated bodies from video sequences. For these tasks, this algorithm requires significantly fewer examples compared to fully-supervised regression algorithms or semi-supervised learning algorithms that do not take the dynamics of the output time series into account.

Canonical Correlation Analysis (CCA) is a well-known technique for finding the correlations between two sets of multi-dimensional variables. It projects both sets of variables into a lower-dimensional space in which they are maximally correlated. CCA is commonly applied for supervised dimensionality reduction, in which one of the multi-dimensional variables is derived from the class label. It has been shown that CCA can be formulated as a least squares problem in the binaryclass case. However, their relationship in the more general setting remains unclear. In this paper, we show that, under a mild condition which tends to hold for high-dimensional data, CCA in multi-label classifications can be formulated as a least squares problem. Based on this equivalence relationship, we propose several CCA extensions including sparse CCA using 1-norm regularization. Experiments on multi-label data sets confirm the established equivalence relationship. Results also demonstrate the effectiveness of the proposed CCA extensions. 1.