The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions. This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of the current state of the field of large-scale image classification and object detection, and compare the state-of-the-art computer vision accuracy with human accuracy. We conclude with lessons learned in the 5 years of the challenge, and propose future directions and improvements.

/pdf/imagenet-large-scale-visual-recognition-challenge-caky5nmmix.pdf

ImageNet Large Scale Visual Recognition Challenge

Prelude. Cycle 1. Introduction. Cycle 2. Structure defines function. Cycle 3. Diversity of cortical functions is provided by inhibition. Cycle 4. Windows on the brain. Cycle 5. A system of rhythms: from simple to complex dynamics. Cycle 6. Synchronization by oscillation. Cycle 7. The brain's default state: self-organized oscillations in rest and sleep. Cycle 8. Perturbation of the default patterns by experience. Cycle 9. The gamma buzz: gluing by oscillations in the waking brain. Cycle 10. Perceptions and actions are brain state-dependent. Cycle 11. Oscillations in the "other cortex:" navigation in real and memory space. Cycle 12. Coupling of systems by oscillations. Cycle 13. The tough problem. References.

Rhythms of the brain

Schultz, Wolfram. Predictive reward signal of dopamine neurons. J. Neurophysiol. 80: 1–27, 1998. The effects of lesions, receptor blocking, electrical self-stimulation, and drugs of abuse suggest t...

/pdf/predictive-reward-signal-of-dopamine-neurons-3f94myirza.pdf

Predictive Reward Signal of Dopamine Neurons

We propose a novel approach to learn and recognize natural scene categories. Unlike previous work, it does not require experts to annotate the training set. We represent the image of a scene by a collection of local regions, denoted as codewords obtained by unsupervised learning. Each region is represented as part of a "theme". In previous work, such themes were learnt from hand-annotations of experts, while our method learns the theme distributions as well as the codewords distribution over the themes without supervision. We report satisfactory categorization performances on a large set of 13 categories of complex scenes.

/pdf/a-bayesian-hierarchical-model-for-learning-natural-scene-zzqtm1es9k.pdf

A Bayesian hierarchical model for learning natural scene categories

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.

/pdf/hierarchical-models-of-object-recognition-in-cortex-33mmp5yhnv.pdf

Hierarchical models of object recognition in cortex

Correction: Animal Detection Precedes Access to Scene Category

A method of performing unsupervised detection of repeating patterns in a series (TS) of events (E21, E12, E5 ...), comprising the steps of: 
a) Providing a plurality of neurons (NR1 - NRP), each neuron being representative of W event types; 
b) Acquiring an input packet (IV) comprising N successive events of the series; 
c) Attributing to at least some neurons a potential value (PT1 - PTP), representative of the number of common events between the input packet and the neuron; 
d) Modify the event types of neurons having a potential value exceeding a first threshold T L ; and 
e) generating a first output signal (OS1 - OSP) for all neurons having a potential value exceeding a second threshold T F , and a second output signal, different from the first one, for all other neurons. A digital integrated circuit configured for carrying out such a method.

Unsupervised detection of repeating patterns in a series of events

Data for: Extremely long-term memory and familiarity after 12 years

Publisher Summary This chapter focuses on neuronal processing related to sensory inputs, intermediate learning processes, and the initiation of motor responses. Experiments related to neural systems that are specialized for three different types of sensory–motor integration were conducted in the rhesus monkey. These experiments described in the chapter revealed different neural systems related to the initiation of responses to food, the prevention of incorrect or punished responses, and the initiation of responses based on the recognition of visual stimuli. In view of this specialization, it follows that when sensory–motor integration is being considered, the type of sensory–motor integration must be specified. In the lateral hypothalamus and substantia innominata, a population of neurons with responses associated with the sight and/or taste of food is found. These neurons only respond to food if the monkey is hungry. Lesions of the orbitofrontal cortex produced deficits. The monkeys continued to respond during extinction to a previously rewarded stimulus. The monkeys were impaired on the reversal of a visual discrimination in that they continued to respond to the previously rewarded stimulus when it was no longer rewarded. The monkeys made errors in Go NoGo tasks in that they responded on the NoGo trials when they should have inhibited responding. There is evidence that a different neural system is involved in responses made on the basis of whether visual stimuli are recognized.

Neuronal processing related to sensory inputs, intermediate learning processes, and the initiation of motor responses

Classification and recognition tasks performed on photonic hardware-based neural networks often require at least one offline computational step, such as in the increasingly popular reservoir computing paradigm. Removing this offline step can significantly improve the response time and energy efficiency of such systems. We present numerical simulations of different algorithms that utilize ultrafast photonic spiking neurons as receptive fields to allow for image recognition without an offline computing step. In particular, we discuss the merits of event, spike-time and rank-order based algorithms adapted to this system. These techniques have the potential to significantly improve the efficiency and effectiveness of optical classification systems, minimizing the number of spiking nodes required for a given task and leveraging the parallelism offered by photonic hardware.

/pdf/online-spike-based-recognition-of-digits-with-ultrafast-1crcw51l.pdf

Simon J. Thorpe

Papers

Correction: Animal Detection Precedes Access to Scene Category

Unsupervised detection of repeating patterns in a series of events

Data for: Extremely long-term memory and familiarity after 12 years

Neuronal processing related to sensory inputs, intermediate learning processes, and the initiation of motor responses

Online spike-based recognition of digits with ultrafast microlaser neurons