PubMed Health⌕ Search

Biomedical subjects

T Poggio

Publications and source records attributed to T Poggio.

At least 19 recordsLinked to original sources
PubMed2001

Multiclass cancer diagnosis using tumor gene expression signatures.

The optimal treatment of patients with cancer depends on establishing accurate diagnoses by using a complex combination of clinical and histopathological data. In some instances, this task is difficult or impossible because of atypical clinical presentation or histopathology. To determine whether the diagnosis of multiple common adult malignancies could be achieved purely by molecular classification, we subjected 218 tumor samples, spanning 14 common tumor types, and 90 normal tissue samples to oligonucleotide microarray gene expression analysis. The expression levels of 16,063 genes and expressed sequence tags were used to evaluate the accuracy of a multiclass classifier based on a support vector machine algorithm. Overall classification accuracy was 78%, far exceeding the accuracy of random classification (9%). Poorly differentiated cancers resulted in low-confidence predictions and could not be accurately classified according to their tissue of origin, indicating that they are molecularly distinct entities with dramatically different gene expression patterns compared with their well differentiated counterparts. Taken together, these results demonstrate the feasibility of accurate, multiclass molecular cancer classification and suggest a strategy for future clinical implementation of molecular cancer diagnostics.

Biomarkers, Tumor↗
PubMed2001

Categorical representation of visual stimuli in the primate prefrontal cortex.

The ability to group stimuli into meaningful categories is a fundamental cognitive process. To explore its neural basis, we trained monkeys to categorize computer-generated stimuli as "cats" and "dogs." A morphing system was used to systematically vary stimulus shape and precisely define the category boundary. Neural activity in the lateral prefrontal cortex reflected the category of visual stimuli, even when a monkey was retrained with the stimuli assigned to new categories.

Animals↗
PubMed2000

Models of object recognition.

Understanding how biological visual systems recognize objects is one of the ultimate goals in computational neuroscience. From the computational viewpoint of learning, different recognition tasks, such as categorization and identification, are similar, representing different trade-offs between specificity and invariance. Thus, the different tasks do not require different classes of models. We briefly review some recent trends in computational vision and then focus on feedforward, view-based models that are supported by psychophysical and physiological data.

Animals↗
PubMed2000

Learning in brains and machines.

The problem of learning is arguably at the very core of the problem of intelligence, both biological and artificial. In this paper we sketch some of our work over the last ten years in the area of supervised learning, focusing on three interlinked directions of research: theory, engineering applications (that is, making intelligent software) and neuroscience (that is, understanding the brain's mechanisms of learning).

Brain↗
PubMed1999

Hierarchical models of object recognition in cortex.

Visual processing in cortex is classically modeled as a hierarchy of increasingly sophisticated representations, naturally extending the model of simple to complex cells of Hubel and Wiesel. Surprisingly, little quantitative modeling has been done to explore the biological feasibility of this class of models to explain aspects of higher-level visual processing such as object recognition. We describe a new hierarchical model consistent with physiological data from inferotemporal cortex that accounts for this complex visual task and makes testable predictions. The model is based on a MAX-like operation applied to inputs to certain cortical neurons that may have a general role in cortical function.

Animals↗
PubMed1998

A Sparse Representation for Function Approximation.

We derive a new general representation for a function as a linear combination of local correlation kernels at optimal sparse locations (and scales) and characterize its relation to principal component analysis, regularization, sparsity principles, and support vector machines.

Journal Article↗
PubMed1997

Top-down learning of low-level vision tasks.

Perceptual tasks such as edge detection, image segmentation, lightness computation and estimation of three-dimensional structure are considered to be low-level or mid-level vision problems and are traditionally approached in a bottom-up, generic and hard-wired way. An alternative to this would be to take a top-down, object-class-specific and example-based approach. In this paper, we present a simple computational model implementing the latter approach. The results generated by our model when tested on edge-detection and view-prediction tasks for three-dimensional objects are consistent with human perceptual expectations. The model's performance is highly tolerant to the problems of sensor noise and incomplete input image information. Results obtained with conventional bottom-up strategies show much less immunity to these problems. We interpret the encouraging performance of our computational model as evidence in support of the hypothesis that the human visual system may learn to perform supposedly low-level perceptual tasks in a top-down fashion.

Algorithms↗
PubMed1996

Role of learning in three-dimensional form perception.

One of the most remarkable characteristics of the human visual system is its ability to perceive specific three-dimensional forms in single two-dimensional contour images. This has often been attributed to a few general purpose and possibly innately specified shape biases, such as those favouring symmetry and other structural regularities (Fig. 1). An alternative approach proposed by the early empiricists and since tested suggests that this ability may also be acquired from visual experience, with the three-dimensional percept being the manifestation of a learned association between specific two-dimensional projections and the correlated three-dimensional structures. These studies of shape learning have been considered inconclusive, however, because their results can potentially be accounted for as cognitive decisions that might have little to do with shape perception per se. Here we present an experimental system that enables objective verification of the role of learning in shape perception by rendering the learning to be perceptually manifest. We show that the human visual system can learn associations between arbitrarily paired two-dimensional pictures and (projectionally consistent) three-dimensional structures. These results implicate high-level recognition processes in the task of shape perception.

Humans↗
PubMed1996

Image representations for visual learning.

Computer vision researchers are developing new approaches to object recognition and detection that are based almost directly on images and avoid the use of intermediate three-dimensional models. Many of these techniques depend on a representation of images that induce a linear vector space structure and in principle requires dense feature correspondence. This image representation allows the use of learning techniques for the analysis of images (for computer vision) as well as for the synthesis of images (for computer graphics).

Artificial Intelligence↗
PubMed1995

Shape representation in the inferior temporal cortex of monkeys.

BACKGROUND: The inferior temporal cortex (IT) of the monkey has long been known to play an essential role in visual object recognition. Damage to this area results in severe deficits in perceptual learning and object recognition, without significantly affecting basic visual capacities. Consistent with these ablation studies is the discovery of IT neurons that respond to complex two-dimensional visual patterns, or objects such as faces or body parts. What is the role of these neurons in object recognition? Is such a complex configurational selectivity specific to biologically meaningful objects, or does it develop as a result of extensive exposure to any objects whose identification relies on subtle shape differences? If so, would IT neurons respond selectively to recently learned views of features of novel objects? The present study addresses this question by using combined psychophysical and electrophysiological experiments, in which monkeys learned to classify and recognize computer-generated three-dimensional objects. RESULTS: A population of IT neurons was found that responded selectively to views of previously unfamiliar objects. The cells discharged maximally to one view of an object, and their response declined gradually as the object was rotated away from this preferred view. No selective responses were ever encountered for views that the animal systematically failed to recognize. Most neurons also exhibited orientation-dependent responses during view-plane rotations. Some neurons were found to be tuned around two views of the same object, and a very small number of cells responded in a view-invariant manner. For the five different objects that were used extensively during the training of the animals, and for which behavioral performance became view-independent, multiple cells were found that were tuned around different views of the same object. A number of view-selective units showed response invariance for changes in the size of the object or the position of its image within the parafovea. CONCLUSION: Our results suggest that IT neurons can develop a complex receptive field organization as a consequence of extensive training in the discrimination and recognition of objects. None of these objects had any prior meaning for the animal, nor did they resemble anything familiar in the monkey's environment. Simple geometric features did not appear to account for the neurons' selective responses. These findings support the idea that a population of neurons--each tuned to a different object aspect, and each showing a certain degree of invariance to image transformations--may, as an ensemble, encode at least some types of complex three-dimensional objects. In such a system, several neurons may be active for any given vantage point, with a single unit acting like a blurred template for a limited neighborhood of a single view.

Animals↗
PubMed1995

Fast perceptual learning in hyperacuity.

We investigated fast improvement of visual performance in several hyperacuity tasks such as vernier acuity and stereoscopic depth perception in almost 100 observers. Results indicate that the fast phase of perceptual learning, occurring within less than 1 hr of training, is specific for the visual field position and for the particular hyperacuity task, but is only partly specific for the eye trained and for the offset tested. Learning occurs without feedback. We conjecture that the site of learning may be quite early in the visual pathway.

Analysis of Variance↗
PubMed1994

View-dependent object recognition by monkeys.

BACKGROUND: How do we recognize visually perceived three-dimensional objects, particularly when they are seen from novel view-points? Recent psychophysical studies have suggested that the human visual system may store a relatively small number of two-dimensional views of a three-dimensional object, recognizing novel views of the object by interpolation between the stored sample views. In order to investigate the neural mechanisms underlying this process, physiological experiments are required and, as a prelude to such experiments, we have been interested to know whether the observations made with human observers extend to monkeys. RESULTS: We trained monkeys to recognize computer-generated images of objects presented from an arbitrarily chosen training view and containing sufficient three-dimensional information to specify the object's structure. We subsequently tested the trained monkeys' ability to generalize recognition of the object to views generated by rotation of the target object around any arbitrary axis. The monkeys recognized as the target only those two-dimensional views that were close to the familiar, training view. Recognition became increasingly difficult for the monkeys as the stimulus was rotated away from the experienced viewpoint, and failed for views farther than about 40 degrees from the training view. This suggests that, in the early stages of learning to recognize a previously unfamiliar object, the monkeys build two-dimensional, viewer-centered object representations, rather than a three-dimensional model of the object. When the animals were trained with as few as three views of the object, 120 degrees apart, they could often recognize all the views of the object resulting from rotations around the same axis. CONCLUSION: Our experiments show that recognition of three-dimensional novel objects is a function of the object's retinal projection. This suggests that non-human primates, like humans, may accomplish view-invariant recognition of familiar objects by a viewer-centered system that interpolates between a small number of stored views. The measures of recognition performance can be simulated by a regularization network that stores a few familiar views, and is endowed with the ability to interpolate between these views. Our results provide the basis for physiological studies of object-recognition by monkeys and suggest that the insights gained from such studies should apply also to humans.

Animals↗
PubMed1994

The importance of symmetry and virtual views in three-dimensional object recognition.

BACKGROUND: Human observers can recognize three-dimensional objects seen in novel orientations, even when they have previously seen only a relatively small number of different views of the object. How our visual system does this is a key problem in vision research. Recent theories and experiments suggest that the human visual system might store a relatively small number of sample two-dimensional views of a three-dimensional object, and recognize novel views by a process of interpolation between the stored sample views. These sample views may be collected during a training phase as the visual system familiarizes itself with the object. RESULTS: Here, we investigate whether constraints on the shapes of objects commonly encountered in the real world can reduce the number of training views required for recognition of three-dimensional objects. We are particularly concerned with the constraint of object symmetry. We show that if an object is bilaterally symmetrical, then additional 'virtual views' can automatically be generated from one sample view by symmetry transformations. These virtual views should make it more easy to recognize novel views of a symmetric than an asymmetric object, when a single sample view has been seen. Recognition should be particularly facilitated when the novel views are close to the virtual view. We present psychophysical results that bear out these predictions. CONCLUSIONS: Our results show that the human visual system can indeed exploit symmetry to facilitate object recognition, and support the model for object recognition in which a small number of two-dimensional views are remembered and combined to recognize novel views of the same object. These results raise questions about how symmetry is recognized, and symmetry transformations implemented, in real, biological neural networks.

Depth Perception↗
PubMed1994

Symmetric 3D objects are an easy case for 2D object recognition.

According to the 1.5-views theorem (Poggio, Technical Report #9005-03, IRST, Povo, 1990; Ullman and Basri, IEEE Trans. PAMI 13, 992-1006, 1991) recognition of a specific 3D object (defined in terms of pointwise features) from a novel 2D view can be achieved from at least two 2D model views (for each object, for orthographic projection). This note considers how recognition can be achieved from a single 2D model view by exploiting prior knowledge of an object's symmetry. It is proved that, for any bilaterally symmetric 3D object, one non-accidental 2D model view is sufficient for recognition since it can be used to generate additional 'virtual' views. It is also proved that, for bilaterally symmetric objects, the correspondence of four points between two views determines the correspondence of all other points. Symmetries of higher order allow the recovery of Euclidean structure from a single 2D view.

Algorithms↗