Jim Mutch

Multiclass Object Recognition with Sparse, Localized Features

We apply a biologically inspired model of visual object recognition to the multiclass object categorization problem. Our model modifies that of Serre, Wolf, and Poggio. As in that work, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways, using simple versions of sparsification and lateral inhibition. We demonstrate the value of retaining some position and scale information above the intermediate feature level. Using feature selection we arrive at a model that performs better with fewer features. Our final model is tested on the Caltech 101 object categories and the UIUC car localization task, in both cases achieving state-of-the-art performance. The results strengthen the case for using this class of model in computer vision.

Object Class Recognition and Localization Using Sparse Features with Limited Receptive Fields

We investigate the role of sparsity and localized features in a biologically-inspired model of visual object classification. As in the model of Serre, Wolf, and Poggio, we first apply Gabor filters at all positions and scales; feature complexity and position/scale invariance are then built up by alternating template matching and max pooling operations. We refine the approach in several biologically plausible ways. Sparsity is increased by constraining the number of feature inputs, lateral inhibition, and feature selection. We also demonstrate the value of retaining some position and scale information above the intermediate feature level. Our final model is competitive with current computer vision algorithms on several standard datasets, including the Caltech 101 object categories and the UIUC car localization task. The results further the case for biologically-motivated approaches to object classification.

Diagnosis by a waiter and a Mars explorer

This paper shows how state-of-the-art state estimation techniques can be used to provide efficient solutions to the difficult problem of real-time diagnosis in mobile robots. The power of the adopted estimation techniques resides in our ability to combine particle filters with classical algorithms, such as Kalman filters. We demonstrate these techniques in two scenarios: a mobile waiter robot and planetary rovers designed by NASA for Mars exploration.

Invariant Recognition Predicts Tuning of Neurons in Sensory Cortex

Tuning properties of simple cells in cortical V1 can be described in terms of a “universal shape” characterized quantitatively by parameter values which hold across different species (Jones and Palmer 1987; Ringach 2002; Niell and Stryker 2008). This puzzling set of findings begs for a general explanation grounded on an evolutionarily important computational function of the visual cortex. We show here that these properties are quantitatively predicted by the hypothesis that the goal of the ventral stream is to compute for each image a “signature” vector which is invariant to geometric transformations (Anselmi et al. 2013b). The mechanism for continuously learning and maintaining invariance may be the memory storage of a sequence of neural images of a few (arbitrary) objects via Hebbian synapses, while undergoing transformations such as translation, scale changes and rotation. For V1 simple cells this hypothesis implies that the tuning of neurons converges to the eigenvectors of the covariance of their input. Starting with a set of dendritic fields spanning a range of sizes, we show with simulations suggested by a direct analysis, that the solution of the associated “cortical equation” effectively provides a set of Gabor-like shapes with parameter values that quantitatively agree with the physiology data. The same theory provides predictions about the tuning of cells in V4 and in the face patch AL (Leibo et al. 2013a) which are in qualitative agreement with physiology data.

Dynamic modelling and control of industrial processes with particle filtering algorithms

Abstract We use a probabilistic approach to estimate the operating conditions and guide an automatic control system for industrial processes. The jump Markov linear Gaussian (JMLG) model is adopted to describe process behavior as a dynamic mixture of linear models. Based on the JMLG model, we use Particle Filtering (PF) algorithms to make real-time estimates of the operating conditions of the process. The PF estimate is used to adapt an automatic feedback control system. We tested our approach against three standard control strategies using a real nonlinear process. The results indicate that implementation of a PF state estimator can lead to better control strategies.

Toward a New Approach for Online Fault Diagnosis Combining Particle Filtering and Parametric Identification

This paper proposes a new approach for online fault diagnosis in dynamic systems, combining a Particle Filtering (PF) algorithm with a classic Fault Detection and Isolation (FDI) framework. Of the two methods, FDI provides deeper insight into a process; however, it cannot normally be computed online. Our approach uses a preliminary PF step to reduce the potential solution space, resulting in an online algorithm with the advantages of both methods. The PF step computes a posterior probability density to diagnose the most probable fault. If the desired confidence is not obtained, the classic FDI framework is invoked. The FDI framework uses recursive parametric estimation for the residual generation block and hypothesis testing and Statistical Process Control (SPC) criteria for the decision making block. We tested the individual methods with an industrial dryer.