Object categorisations using templates constructed from multi-scale line and edge representations

Object categorisation is linked to detection, segregation and recognition. In the visual system, these processes are achieved in the ventral \what"and dorsal \where"pathways [3], with bottom-up feature extractions in areas V1, V2, V4 and IT (what) in parallel with top-down attention from PP via MT to V2 and V1 (where). The latter is steered by object templates in memory, i.e. in prefrontal cortex with a what component in PF46v and a where component in PF46d.

An integrated framework for combining gist vision with object segregation categorisation and recognition

There are roughly two processing systems: (1) very fast gist vision of entire scenes, completely bottom-up and data driven, and (2) Focus-of-Attention (FoA) with sequential screening of specific image regions and objects. The latter system has to be sequential because unnormalised input objects must be matched against normalised templates of canonical object views stored in memory, which involves dynamic routing of features in the visual pathways.

Invariant multi-scale object categorisation and recognition

Object recognition requires that templates with canonical views are stored in memory. Such templates must somehow be normalised. In this paper we present a novel method for obtaining 2D translation, rotation and size invariance. Cortical simple, complex and end-stopped cells provide multi-scale maps of lines, edges and keypoints. These maps are combined such that objects are characterised. Dynamic routing in neighbouring neural layers allows feature maps of input objects and stored templates to converge. We illustrate the construction of group templates and the invariance method for object categorisation and recognition in the context of a cortical architecture, which can be applied in computer vision.

Cortical 3D face and object recognition using 2D projections

Empirical studies concerning face recognition suggest that faces may be stored in memory by a few canonical representations. In cortical area V1 exist double-opponent colour blobs, also simple, complex and end-stopped cells which provide input for a multiscale line/edge representation, keypoints for dynamic feature routine, and saliency maps for Focus-of-Attention.

Software transactional memory as a building block for parallel embedded realtime systems

The recent trends of chip architectures with higher number of heterogeneous cores, and non-uniform memory/non-coherent caches, brings renewed attention to the use of Software Transactional Memory (STM) as a fundamental building block for developing parallel applications. Nevertheless, although STM promises to ease concurrent and parallel software development, it relies on the possibility of aborting conflicting transactions to maintain data consistency, which impacts on the responsiveness and timing guarantees required by embedded real-time systems. In these systems, contention delays must be (efficiently) limited so that the response times of tasks executing transactions are upper-bounded and task sets can be feasibly scheduled. In this paper we assess the use of STM in the development of embedded real-time software, defending that the amount of contention can be reduced if read-only transactions access recent consistent data snapshots, progressing in a wait-free manner. We show how the required number of versions of a shared object can be calculated for a set of tasks. We also outline an algorithm to manage conflicts between update transactions that prevents starvation.

Disambiguating the Effects of Social Instability Stress in Adolescence on Learning and Memory Tasks that Involve the Medial Prefrontal Cortex and Hippocampus

Exposure to chronic stress can alter the structure and function of brain regions involved in learning and memory, and these effects are typically long-lasting if the stress occurs during sensitive periods of development. Until recently, adolescence has received relatively little attention as a sensitive period of development, despite marked changes in behaviour, heightened reactivity to stressors, and cognitive and neural maturation. Therefore, the purpose of the present study was to investigate the long-term effects of chronic stress in adolescence on two spatial learning and memory tasks (Morris water maze and Spatial Object Location test) and on a working memory task (Delayed Alternation task). Male rats were randomly assigned to chronic social instability stress (SS; daily 1 hour isolation and subsequent change of cage partner between postnatal days 30 and 45) or to a no-stress control group (CTL). During acquisition learning in the Morris water maze task, SS rats demonstrated impaired long-term memory for the location of the hidden escape platform compared to CTL rats, although the impairment was only seen after the first day of training. Similarly, SS rats had impaired long-term memory in the Spatial Object Location test after a long delay (240 minutes), but not after shorter delays (15 or 60 minutes) compared to CTL rats. On the Delayed Alternation task, which assessed working memory across delays ranging from 5 to 90 seconds, no group differences were observed. These results are partially in line with previous research that revealed adult impairment on spatial learning and memory tasks after exposure to chronic social instability stress in adolescence. The observed deficits, however, appear to be limited to long-term memory as no group differences were observed during brief periods of retention.

Encountering the suffering other in illness narratives : between the memory of suffering and the suffering memory

Cette étude porte sur la dimension intersubjective de la souffrance qui affecte le rapport du souffrant à son corps, au temps et à l’espace vécus de même que son identité narrative et sa mémoire narrative. Mon argument principal est que la voix narrative constitue le rapport intersubjectif dans les récits de maladie que les proches écrivent sur leurs partenaires souffrant de cancer de cerveau ou de la maladie d’Alzheimer. Ma discussion est basée sur l’éthique, la phénoménologie, les théories de l’incorporation, les études des récits de vie, la sociologie et l’anthropologie médicales et la narratologie. L’objet de mon étude est l’expérience incorporée de la souffrance dans les récits de maladie et je me concentre sur la souffrance comme perte de la mémoire et du soi narratif. J’analyse le journal How Linda Died de Frank Davey et les mémoires de John Bayley, Iris: A Memoir of Iris Murdoch et Iris and Her Friends: A Memoir of Memory and Desire. J’explore comment les récits de maladie constituent le rapport éthique à l’Autre souffrant de la rupture de la mémoire. La discussion de la voix est située dans le contexte des récits de vie et se propose de dépasser les limites des approches sociologiques et anthropologiques de la voix dans les récits de maladie. Dans ce sens, dans un premier temps je porte mon attention sur des études narratologiques de la voix en indiquant leurs limites. Ma propre définition de la voix narrative est basée sur l’éthique dans la perspective d’Emmanuel Levinas et de Paul Ricœur, sur l’interprétation du temps, de la mémoire et de l’oubli chez St-Augustin et la discussion levinasienne de la constitution intersubjective du temps. J’avance l’idée que la “spontanéité bienveillante” (Ricœur, Soi-même comme un autre 222) articule la voix narrative et l’attention envers l’Autre souffrant qui ne peut plus se rappeler, ni raconter sa mémoire. En reformulant la définition augustinienne du temps qui met en corrélation les modes temporels avec la voix qui récite, j’avance l’idée que la voix est distendue entre la voix présente de la voix présente, la voix présente de la voix passée, la voix présente de la voix future. Je montre comment la voix du soignant est inscrite par et s’inscrit dans les interstices d’une voix interrompue, souffrante. Je définis les récits de vies comme des interfaces textuelles entre le soi et l’Autre, entre la voix du soi et la voix du souffrant, comme un mode de restaurer l’intégrité narrative de l’Autre.

Observations on Cortical Mechanisms for Object Recognition andsLearning

This paper sketches a hypothetical cortical architecture for visual 3D object recognition based on a recent computational model. The view-centered scheme relies on modules for learning from examples, such as Hyperbf-like networks. Such models capture a class of explanations we call Memory-Based Models (MBM) that contains sparse population coding, memory-based recognition, and codebooks of prototypes. Unlike the sigmoidal units of some artificial neural networks, the units of MBMs are consistent with the description of cortical neurons. We describe how an example of MBM may be realized in terms of cortical circuitry and biophysical mechanisms, consistent with psychophysical and physiological data.

Translation Invariance in Object Recognition, and Its Relation to Other Visual Transformations

Human object recognition is generally considered to tolerate changes of the stimulus position in the visual field. A number of recent studies, however, have cast doubt on the completeness of translation invariance. In a new series of experiments we tried to investigate whether positional specificity of short-term memory is a general property of visual perception. We tested same/different discrimination of computer graphics models that were displayed at the same or at different locations of the visual field, and found complete translation invariance, regardless of the similarity of the animals and irrespective of direction and size of the displacement (Exp. 1 and 2). Decisions were strongly biased towards same decisions if stimuli appeared at a constant location, while after translation subjects displayed a tendency towards different decisions. Even if the spatial order of animal limbs was randomized ("scrambled animals"), no deteriorating effect of shifts in the field of view could be detected (Exp. 3). However, if the influence of single features was reduced (Exp. 4 and 5) small but significant effects of translation could be obtained. Under conditions that do not reveal an influence of translation, rotation in depth strongly interferes with recognition (Exp. 6). Changes of stimulus size did not reduce performance (Exp. 7). Tolerance to these object transformations seems to rely on different brain mechanisms, with translation and scale invariance being achieved in principle, while rotation invariance is not.

Optimising memory usage in n-tuple neural networks

The use of n-tuple or weightless neural networks as pattern recognition devices is well known (Aleksander and Stonham, 1979). They have some significant advantages over the more common and biologically plausible networks, such as multi-layer perceptrons; for example, n-tuple networks have been used for a variety of tasks, the most popular being real-time pattern recognition, and they can be implemented easily in hardware as they use standard random access memories. In operation, a series of images of an object are shown to the network, each being processed suitably and effectively stored in a memory called a discriminator. Then, when another image is shown to the system, it is processed in a similar manner and the system reports whether it recognises the image; is the image sufficiently similar to one already taught? If the system is to be able to recognise and discriminate between m-objects, then it must contain m-discriminators. This can require a great deal of memory. This paper describes various ways in which memory requirements can be reduced, including a novel method for multiple discriminator n-tuple networks used for pattern recognition. By using this method, the memory normally required to handle m-objects can be used to recognise and discriminate between 2^m — 2 objects.

A pilot study investigating the effects of a single dose of a flavonoid-rich blueberry drink on memory in 8-10 year old children

Recent evidence from animal and adult human subjects has demonstrated potential benefits to cognition from flavonoid supplementation. This study aimed to investigate whether these cognitive benefits extended to a sample of school-aged children. Using a cross-over design, with a wash out of at least seven days between drinks, fourteen 8-10 year old children consumed either a flavonoid-rich blueberry drink or matched vehicle. Two hours after consumption, subjects completed a battery of five cognitive tests comprising the Go-NoGo, Stroop, Rey’s Auditory Verbal Learning Task, Object Location Task, and a Visual N-back. In comparison to vehicle, the blueberry drink produced significant improvements in the delayed recall of a previously learned list of words, showing for the first time a cognitive benefit for acute flavonoid intervention in children. However, performance on a measure of proactive interference indicated that the blueberry intervention led to a greater negative impact of previously memorised words on the encoding of a set of new words. There was no benefit of our blueberry intervention for measures of attention, response inhibition or visuo-spatial memory. While findings are mixed, the improvements in delayed recall found in this pilot study suggest that, following acute flavonoid-rich blueberry interventions, school aged children encode memory items more effectively.

Memory-rescuing effects of cannabidiol in an animal model of cognitive impairment relevant to neurodegenerative disorders

Rationale Cannabidiol, the main nonpsychotropic constituent of Cannabis sativa, possesses a large number of pharmacological effects including anticonvulsive, sedative, hypnotic, anxiolytic, antipsychotic, anti-inflammatory, and neuroprotective, as demonstrated in clinical and preclinical studies. Many neurodegenerative disorders involve cognitive deficits, and this has led to interest in whether cannabidiol could be useful in the treatment of memory impairment associated to these diseases. Objectives We used an animal model of cognitive impairment induced by iron overload in order to test the effects of cannabidiol in memory-impaired rats. Methods Rats received vehicle or iron at postnatal days 12-14. At the age of 2 months, they received an acute intraperitoneal injection of vehicle or cannabidiol (5.0 or 10.0 mg/kg) immediately after the training session of the novel object recognition task. In order to investigate the effects of chronic cannabidiol, iron-treated rats received daily intraperitoneal injections of cannabidiol for 14 days. Twenty-four hours after the last injection, they were submitted to object recognition training. Retention tests were performed 24 h after training. Results A single acute injection of cannabidiol at the highest dose was able to recover memory in iron-treated rats. Chronic cannabidiol improved recognition memory in iron-treated rats. Acute or chronic cannabidiol does not affect memory in control rats. Conclusions The present findings provide evidence suggesting the potential use of cannabidiol for the treatment of cognitive decline associated with neurodegenerative disorders. Further studies, including clinical trials, are warranted to determine the usefulness of cannabidiol in humans suffering from neurodegenerative disorders.

Role of nitric oxide and endocannabinoids in synaptic plasticity in the perirhinal cortex and in visual recognition memory

Introduction and aims of the research Nitric oxide (NO) and endocannabinoids (eCBs) are major retrograde messengers, involved in synaptic plasticity (long-term potentiation, LTP, and long-term depression, LTD) in many brain areas (including hippocampus and neocortex), as well as in learning and memory processes. NO is synthesized by NO synthase (NOS) in response to increased cytosolic Ca2+ and mainly exerts its functions through soluble guanylate cyclase (sGC) and cGMP production. The main target of cGMP is the cGMP-dependent protein kinase (PKG). Activity-dependent release of eCBs in the CNS leads to the activation of the Gαi/o-coupled cannabinoid receptor 1 (CB1) at both glutamatergic and inhibitory synapses. The perirhinal cortex (Prh) is a multimodal associative cortex of the temporal lobe, critically involved in visual recognition memory. LTD is proposed to be the cellular correlate underlying this form of memory. Cholinergic neurotransmission has been shown to play a critical role in both visual recognition memory and LTD in Prh. Moreover, visual recognition memory is one of the main cognitive functions impaired in the early stages of Alzheimer’s disease. The main aim of my research was to investigate the role of NO and ECBs in synaptic plasticity in rat Prh and in visual recognition memory. Part of this research was dedicated to the study of synaptic transmission and plasticity in a murine model (Tg2576) of Alzheimer’s disease. Methods Field potential recordings. Extracellular field potential recordings were carried out in horizontal Prh slices from Sprague-Dawley or Dark Agouti juvenile (p21-35) rats. LTD was induced with a single train of 3000 pulses delivered at 5 Hz (10 min), or via bath application of carbachol (Cch; 50 μM) for 10 min. LTP was induced by theta-burst stimulation (TBS). In addition, input/output curves and 5Hz-LTD were carried out in Prh slices from 3 month-old Tg2576 mice and littermate controls. Behavioural experiments. The spontaneous novel object exploration task was performed in intra-Prh bilaterally cannulated adult Dark Agouti rats. Drugs or vehicle (saline) were directly infused into the Prh 15 min before training to verify the role of nNOS and CB1 in visual recognition memory acquisition. Object recognition memory was tested at 20 min and 24h after the end of the training phase. Results Electrophysiological experiments in Prh slices from juvenile rats showed that 5Hz-LTD is due to the activation of the NOS/sGC/PKG pathway, whereas Cch-LTD relies on NOS/sGC but not PKG activation. By contrast, NO does not appear to be involved in LTP in this preparation. Furthermore, I found that eCBs are involved in LTP induction, but not in basal synaptic transmission, 5Hz-LTD and Cch-LTD. Behavioural experiments demonstrated that the blockade of nNOS impairs rat visual recognition memory tested at 24 hours, but not at 20 min; however, the blockade of CB1 did not affect visual recognition memory acquisition tested at both time points specified. In three month-old Tg2576 mice, deficits in basal synaptic transmission and 5Hz-LTD were observed compared to littermate controls. Conclusions The results obtained in Prh slices from juvenile rats indicate that NO and CB1 play a role in the induction of LTD and LTP, respectively. These results are confirmed by the observation that nNOS, but not CB1, is involved in visual recognition memory acquisition. The preliminary results obtained in the murine model of Alzheimer’s disease indicate that deficits in synaptic transmission and plasticity occur very early in Prh; further investigations are required to characterize the molecular mechanisms underlying these deficits.

Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

Imagery of a moving object: the role of occipital cortex and human MT/V5+

Visual imagery – similar to visual perception – activates feature-specific and category-specific visual areas. This is frequently observed in experiments where the instruction is to imagine stimuli that have been shown immediately before the imagery task. Hence, feature-specific activation could be related to the short-term memory retrieval of previously presented sensory information. Here, we investigated mental imagery of stimuli that subjects had not seen before, eliminating the effects of short-term memory. We recorded brain activation using fMRI while subjects performed a behaviourally controlled guided imagery task in predefined retinotopic coordinates to optimize sensitivity in early visual areas. Whole brain analyses revealed activation in a parieto-frontal network and lateral–occipital cortex. Region of interest (ROI) based analyses showed activation in left hMT/V5+. Granger causality mapping taking left hMT/V5+ as source revealed an imagery-specific directed influence from the left inferior parietal lobule (IPL). Interestingly, we observed a negative BOLD response in V1–3 during imagery, modulated by the retinotopic location of the imagined motion trace. Our results indicate that rule-based motion imagery can activate higher-order visual areas involved in motion perception, with a role for top-down directed influences originating in IPL. Lower-order visual areas (V1, V2 and V3) were down-regulated during this type of imagery, possibly reflecting inhibition to avoid visual input from interfering with the imagery construction. This suggests that the activation in early visual areas observed in previous studies might be related to short- or long-term memory retrieval of specific sensory experiences.