Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “representation learning”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 91 records · Page 5Linked to original sources
PubMed2002

Associative learning and elemental representation: II. Generalization and discrimination.

This paper follows on from an earlier companion paper (McLaren & Mackintosh, 2000), in which we further developed the elemental associative theory put forward in McLaren, Kaye, and Mackintosh (1989). Here, we begin by explicating the idea that stimuli can be represented as patterns of activation distributed across a set of units and that different stimuli activate partially overlapping sets (the degree of overlap being proportional to the similarity of the stimuli). A consequence of this view is that the overall level of activity of some of the units representing a stimulus may be dependent on the nature of the other stimuli present at the same time. This allows an elemental analysis in which provision for the representation of configurations of stimuli is made. A selective review of studies of generalization and discrimination learning, including peak shift, transfer along a continuum, configural discrimination, and summation, suggests that the principles embodied in this class of theory deserve careful consideration and will form part of any successful model of associative learning in humans or animals. There are some phenomena that require an elemental/associative explanation.

Association Learning↗
PubMed1992

Combining exemplar-based category representations and connectionist learning rules.

Adaptive network and exemplar-similarity models were compared on their ability to predict category learning and transfer data. An exemplar-based network (Kruschke, 1990a, 1990b, 1992) that combines key aspects of both modeling approaches was also tested. The exemplar-based network incorporates an exemplar-based category representation in which exemplars become associated to categories through the same error-driven, interactive learning rules that are assumed in standard adaptive networks. Experiment 1, which partially replicated and extended the probabilistic classification learning paradigm of Gluck and Bower (1988a), demonstrated the importance of an error-driven learning rule. Experiment 2, which extended the classification learning paradigm of Medin and Schaffer (1978) that discriminated between exemplar and prototype models, demonstrated the importance of an exemplar-based category representation. Only the exemplar-based network accounted for all the major qualitative phenomena; it also achieved good quantitative predictions of the learning and transfer data in both experiments.

Concept Formation↗
PubMed1990

Hippocampal representation in place learning.

The generality of the place-learning impairment associated with hippocampal system damage was challenged using methods of training that permitted subjects to form an individual association between the place of escape and a particular navigational route in an open-field water maze. Both normal rats and rats with fornix lesions (FX rats) acquired this task rapidly, although FX rats were slightly slower in achieving minimum escape latencies. In postcriterion testing, FX rats occasionally made near misses but, more often, their escape performance was indistinguishable from that of intact rats. Results from a variety of probe tests indicated that FX rats, like normal rats, had based their performance on a representation of multiple distal cues but their representation, unlike that of normal rats, was inflexible in that it could not be used to guide performance when the cues or starting position were altered. These results parallel those from other studies of hippocampal function in animals and humans: The learning deficit consequent to hippocampal system damage (1) is not specific to a particular category of learning materials, but is dependent on the representational demands of the task; (2) is observed when task demands encourage a representation based on relations among multiple cues, but not when the task encourages adaptation to an individual (or compound) stimulus; (3) spares acquisition of fundamental procedures needed to perform the task; and (4) impairs the flexible use of learned information in tests other than repetition of the learning experience.

Animals↗
PubMed2001

A variational method for learning sparse and overcomplete representations.

An expectation-maximization algorithm for learning sparse and overcomplete data representations is presented. The proposed algorithm exploits a variational approximation to a range of heavy-tailed distributions whose limit is the Laplacian. A rigorous lower bound on the sparse prior distribution is derived, which enables the analytic marginalization of a lower bound on the data likelihood. This lower bound enables the development of an expectation-maximization algorithm for learning the overcomplete basis vectors and inferring the most probable basis coefficients.

Journal Article↗
PubMed2003

Dictionary learning algorithms for sparse representation.

Algorithms for data-driven learning of domain-specific overcomplete dictionaries are developed to obtain maximum likelihood and maximum a posteriori dictionary estimates based on the use of Bayesian models with concave/Schur-concave (CSC) negative log priors. Such priors are appropriate for obtaining sparse representations of environmental signals within an appropriately chosen (environmentally matched) dictionary. The elements of the dictionary can be interpreted as concepts, features, or words capable of succinct expression of events encountered in the environment (the source of the measured signals). This is a generalization of vector quantization in that one is interested in a description involving a few dictionary entries (the proverbial "25 words or less"), but not necessarily as succinct as one entry. To learn an environmentally adapted dictionary capable of concise expression of signals generated by the environment, we develop algorithms that iterate between a representative set of sparse representations found by variants of FOCUSS and an update of the dictionary using these sparse representations. Experiments were performed using synthetic data and natural images. For complete dictionaries, we demonstrate that our algorithms have improved performance over other independent component analysis (ICA) methods, measured in terms of signal-to-noise ratios of separated sources. In the overcomplete case, we show that the true underlying dictionary and sparse sources can be accurately recovered. In tests with natural images, learned overcomplete dictionaries are shown to have higher coding efficiency than complete dictionaries; that is, images encoded with an overcomplete dictionary have both higher compression (fewer bits per pixel) and higher accuracy (lower mean square error).

Algorithms↗
PubMed2001

Altering object representations through category learning.

Previous research has shown that objects that are grouped together in the same category become more similar to each other and that objects that are grouped in different categories become increasingly dissimilar, as measured by similarity ratings and psychophysical discriminations. These findings are consistent with two theories of the influence of concept learning on similarity. By a Strategic Judgment Bias account, the categories associated with objects are explicitly used as cues for determining similarity, and objects that are categorized together are judged to be more similar because similarity is not only a function of the objects themselves, but also the objects' category labels. By a Changed Object Description account, category learning alters the description of the objects themselves, emphasizing properties that are relevant for categorization. A new method for distinguishing between these accounts is introduced which measures the difference between the similarity ratings of categorized objects to a neutral object. The results indicate both strategic biases based on category labels and genuine representational change, with the strategic bias affecting mostly objects belonging to different categories and the representational change affecting mostly objects belonging to the same category.

Adult↗
PubMed2004

Human orbitofrontal cortex mediates extinction learning while accessing conditioned representations of value.

In extinction, an animal learns that a previously conditioned stimulus (CS+) no longer predicts delivery of a salient reinforcer (unconditioned stimulus, UCS). Rodent studies indicate that extinction relies on amygdala-prefrontal interactions and involves formation of memories that inhibit, without actually erasing, the original conditioning trace. Whether extinction learning in humans follows similar neurobiological principles is unknown. We used functional magnetic resonance imaging to measure human brain activity evoked during olfactory aversive conditioning and extinction learning. Neural responses in orbitofrontal cortex and amygdala were preferentially enhanced during extinction, suggesting potential cross-species preservation of learning mechanisms that oppose conditioning. Moreover, by manipulating UCS aversiveness via reinforcer inflation, we showed that a CS+ retains access to representations of UCS value in distinct regions of ventral prefrontal cortex, even as extinction proceeds.

Adolescent↗
PubMed2001

Rapid regulation of GAD67 mRNA and protein level in cortical neurons after sensory learning.

Cortical representations of different modalities can be modified by sensory learning. Our previous studies in the barrel cortex showed that expansion of the cortical representation of a row of vibrissae could be induced by pairing stimulation of a row of vibrissae with a tail shock. The plastic change in cortical reactivity to the input used during the training was accompanied by increased density of GABA immunoreactive neurons in the involved row of cortical barrels. Using the same paradigm, the present study examined the pathway of GABA synthesis-expression of GAD67 mRNA and immunoreactivity of GAD67 isoenzyme in the barrel cortex of mice after sensory learning. In situ hybridization revealed that the GAD67 mRNA level was elevated in one row of barrels in the trained group as well as in controls receiving vibrissae stimulation alone. In contrast, elevation of immunoreactivity of the GAD67 protein occurred only in the trained group. The density of GABA-immunoreactive neurons in the hollows of barrels representing the row of vibrissae activated during the training was increased by 50%. These data indicated that sensory stimulation alone affected expression of the 67 kDa glutamate decarboxylase isoenzyme synthesis pathway, whereas the processes involved in cortical plasticity induced by associative learning modified this pathway additionally at the level of translation.

Animals↗
PubMedDate not supplied

Vector representation of associative learning.

I. P. Pavlov has shown that conditioned reflexes are selective both with respect to conditioned stimuli and to conditioned reflexes elicited by those conditioned stimuli. At the neuronal level, selective aspects of conditional stimuli are based on detectors selectively tuned to the respective stimuli. The selective aspects of conditioned reflexes are due to command neurons representing specific unconditioned reflexes. It can be assumed that conditioned reflexes result from association between selective detectors and specific command neurons. The detectors activated by a conditional stimulus constitute a combination of excitations--a detector excitation vector. The detector excitation vector acts on a command neuron via a set of plastic synapses--a synaptic weight vector. Plastic synapses are modified in the process of learning, making the command neuron selectively tuned to a specific conditioned stimulus. The selective tuning of a particular command neuron to a specific excitation vector referred to a conditioned stimulus is the basis of associative learning. The probabilities of conditioned reflexes elicited by conditional and differential stimuli implicitly contain information concerning excitation vectors that encode the respective stimuli. The contribution of the vector code to associative learning was explored combining differential color conditioning with intracellular recording from color-coding neurons. It is shown that colors in carps and monkeys are represented on a hypersphere in the four-dimensional space similar with human color space. The basis of the color space is constituted by red-green, blue-yellow, brightness, and darkness neurons.

Association Learning↗
PubMedDate not supplied

Vector representation of associative learning.

I. P. Pavlov [12] has shown that conditioned reflexes are selective both with respect to conditioned stimuli and to conditioned reflexes elicited by those conditioned stimuli. At the neuronal level selective aspects of conditioned stimuli are based on detectors selectively tuned to respective stimuli. The selective aspects of conditioned reflexes are due to command neurons representing specific unconditioned reflexes. It can be assumed that conditioned reflexes result from association between selective detectors and specific command neurons. The detectors activated by a conditioned stimulus constitute a combination of excitations--a detector excitation vector. The detector excitation vector acts on a command neuron via a set of plastic synapses--a synaptic weight vector. Plastic synapses are modified in the process of learning making command neuron selectively tuned to a specific conditioned stimulus. The selective tuning of a particular command neuron to a specific excitation vector referred to a conditioned stimulus is a basis of associative learning. The probabilities of conditioned reflexes elicited by conditioned and differential stimuli implicitly contain information concerning excitation vectors that encode respective stimuli. Contribution of the vector code to associative learning was explored combining differential color conditioning with intracellular recording from color-coding neurons. It was shown that colors in carps and monkeys are represented on a hypersphere in the four-dimensional space similar to human color space. The basis of the color space is constituted by red-green, blue-yellow, brightness and darkness neurons.

Animals↗
PubMed2004

Representation of well-learned information in the monkey hippocampus.

In the neocortex, extensive training results in enhanced neuronal selectivity for learned stimuli relative to novel stimuli. This enhanced selectivity has been taken as evidence for learning-related plasticity. Much less is known, in contrast, about the representation of well-learned information in the hippocampus. In this study, we examined the responses of individual hippocampal neurons to well-learned and novel stimuli presented in the context of an associative learning task. There was no difference in the response magnitude or visual response latency of hippocampal neurons to the well-learned and novel stimuli. In contrast, hippocampal neurons responded significantly more selectively to the well-learned stimuli relative to the novel stimuli. These findings show that hippocampal cells, like neocortical cells, show greater selectivity to well-learned stimuli compared to novel stimuli.

Animals↗
PubMed2025

Orthrus: Towards Evolutionary and Functional RNA Foundation Models.

In the face of rapidly accumulating genomic data, our ability to accurately predict key mature RNA properties that underlie transcript function and regulation remains limited. Pre-trained genomic foundation models offer an avenue to adapt learned RNA representations to biological prediction tasks. However, existing genomic foundation models are trained using strategies borrowed from textual domains that do not leverage biological domain knowledge. Here, we introduce Orthrus, a Mamba-based mature RNA foundation model pre-trained using a novel self-supervised contrastive learning objective with biological augmentations. Orthrus is trained by maximizing embedding similarity between curated pairs of RNA transcripts, where pairs are formed from splice isoforms of 10 model organisms and transcripts from orthologous genes in 400+ mammalian species from the Zoonomia Project. This training objective results in a latent representation that clusters RNA sequences with functional and evolutionary similarities. We find that the generalized mature RNA isoform representations learned by Orthrus significantly outperform genomic foundation models on mRNA property prediction tasks, and requires only a fraction of fine-tuning data to do so. Finally, we show that Orthrus is capable of capturing divergent biological function of individual transcript isoforms.

Journal Article↗
PubMed2025

A multi-modal transformer for cell type-agnostic regulatory predictions.

Sequence-based deep learning models have emerged as powerful tools for deciphering the cis-regulatory grammar of the human genome but cannot generalize to unobserved cellular contexts. Here, we present EpiBERT, a multi-modal transformer that learns generalizable representations of genomic sequence and cell type-specific chromatin accessibility through a masked accessibility-based pre-training objective. Following pre-training, EpiBERT can be fine-tuned for gene expression prediction, achieving accuracy comparable to the sequence-only Enformer model, while also being able to generalize to unobserved cell states. The learned representations are interpretable and useful for predicting chromatin accessibility quantitative trait loci (caQTLs), regulatory motifs, and enhancer-gene links. Our work represents a step toward improving the generalization of sequence-based deep neural networks in regulatory genomics.

Humans↗
PubMed2004

Reinforcement learning with via-point representation.

In this paper, we propose a new learning framework for motor control. This framework consists of two components: reinforcement learning and via-point representation. In the field of motor control, conventional reinforcement learning has been used to acquire control sequences such as cart-pole or stand-up robot control. Recently, researchers have become interested in hierarchical architecture, such as multiple levels, and multiple temporal and spatial scales. Our new framework contains two levels of hierarchical architecture. The higher level is implemented using via-point representation, which corresponds to macro-actions or multiple time scales. The lower level is implemented using a trajectory generator that produces primitive actions. Our framework can modify the ongoing movement by means of temporally localized via-points and trajectory generation. Successful results are obtained in computer simulation of the cart-pole swing up task.

Computer Simulation↗
PubMed1992

A sensorimotor basis for motor learning: evidence indicating specificity of practice.

Our previous work (Proteau, Marteniuk, Girouard, & Dugas, 1987) was concerned with determining whether with relatively extensive practice on a movement aiming task, as the skill theoretically starts becoming open-loop, there would be evidence for a decreasing emphasis on visual feedback for motor control. We eliminated vision of the moving limb after moderate and extensive practice and found that the movement became more dependent on this feedback with greater amounts of practice. In the present study, we wished to test the hypothesis, developed from our previous work, that at the base of movement learning is a sensorimotor representation that consists of integrated information from central processes and sensory feedback derived from previous experiences on the movement task. A strong test of this hypothesis would be the prediction that for an aiming task, the addition of vision, after moderate and relatively extensive practice without vision, would lead to an increasingly large movement decrement, relative to appropriate controls. We found good support for this prediction. From these and our previous results, and the idea of the sensorimotor representation underlying learning, we develop the idea that learning is specific to the conditions that prevail during skill acquisition. This has implications for the ideas of the generalized motor program and schema theory.

Feedback↗
PubMed1998

Basing categorization on individuals and events.

Exemplar, prototype, and connectionist models typically assume that events constitute the basic unit of learning and representation in categorization. In these models, each learning events updates a statistical representation of a category independently of other learning events. An implication is that events involving the same individual affect learning independently and are not integrated into a single structure that represents the individual in an internal model of the world. A series of experiments demonstrates that human subjects track individuals across events, establish representations of them, and use these representations in categorization. These findings are consistent with "representationalism," the view that an internal model of the world constitutes a physical level of representation in the brain, and that the brain does not simply capture the statistical properties of events in an undifferentiated dynamical system. Although categorization is an inherently statistical process that produces generalization, pattern completion, frequency effects, and adaptive learning, it is also an inherently representational process that establishes an internal model of the world. As a result, representational structures evolve in memory to track the histories of individuals, accumulate information about them, and simulate them in events.

Humans↗
PubMed2003

Spatial representation of predictive motor learning.

A key feature of skilled motor behavior is the ability of the CNS to predict the consequences of its actions. Such prediction occurs when one hand pulls on an object held in the other hand; the restraining hand generates an anticipatory increase in grip force, thereby preventing the object from slipping. When manipulating a novel object, the CNS adapts its predictive response to ensure that predictions are accurately tuned to the dynamics of the object. Here we examine whether learning to predict the consequences of an action on a novel object is restricted to the actions performed during manipulation or generalizes to novel actions. A bimanual task in which subjects held an object in each hand and the relationship between actions on one object and the motion of the other could be computer controlled from trial-to-trial was used. In four conditions we varied the spatial relationship between the direction of force subjects applied to the left-hand object and the consequent direction of motion of an object held in their right hand, which subjects were required to restrain. The results show that predictive learning was local to the direction of forces experienced during learning and that the magnitude of predictive responses was greatly reduced for novel directions of action of the left hand. The pattern of generalization shows that the representation of predictive learning is spatially local and can be approximated as having a spatially narrow Gaussian basis function.

Conditioning, Psychological↗