In-place Learning Research Articles

Unpacking place-based narratives: enhancing campus community participation in watershed conservation

Purpose The study aims to identify the evoked “sense of place” that the campus community attributes to a watershed area in a Malaysian higher institution, aiming to enhance their participation in watershed conservation. Central to this objective is the incorporation of the concept of a watershed as a place, serving as the conceptual framework for analysis. Design/methodology/approach This case study explores an urban lake at Universiti Malaya, Malaysia’s oldest higher institution. It uses diverse qualitative data, including document analysis, semi-structured interviews, vox-pop interviews and a co-production workshop, to generate place-based narratives reflecting the meanings and values that staff and students associate with the watershed. Thematic analysis is then applied for further examination. Findings The data patterns reveal shared sense of place responses on: campus as a historic place, student, staff and campus identity, in-place learning experiences and interweaving of community well-being and watershed health. Recommendations advocate translating these narratives into campus sustainability communication through empirical findings and continuous co-production of knowledge and strategies with the campus community. Practical implications The research findings play a critical role in influencing sustainable campus planning and community inclusion by integrating place-based frameworks into sustainable development and watershed management. The study recommends the process of identifying place-based narratives with implications for the development of sustainability communication in a campus environment. Originality/value This paper contributes both conceptually and empirically to the sustainable management of a campus watershed area through place-based thinking. It outlines a process for enhancing campus sustainability communication strategies.

Evaluation of sustainable, blended learning workforce education for suicide prevention in youth services

Suicide is the second leading cause of death for youth in the U.S. and equipping clinical and non-clinical staff in youth services to address suicide concerns is a challenge. This paper evaluates InPlace Learning, an innovative and sustainable blended learning approach to suicide prevention workforce education in youth services. InPlace Learning combines group video-guided workshops, follow-up Q&A via web-based ‘office hours’, and continual learning through job aids and brief refreshers. Hillside identified 25 programs to adopt InPlace Learning for suicide prevention training, and 1,162 staff to participate in the training. The purpose of the first phase of this program evaluation was to evaluate the feasibility of this approach, including examining adoption and reach of InPlace Learning, as well as education outcomes for staff, including knowledge, self-efficacy, and transfer of learning. The program evaluation sample consisted of 556 staff who completed post-training evaluations. Ten staff shared their experience and feedback through post-training interviews. Results show that 100 % (N = 25) of programs adopted InPlace Learning and 64 % of staff participated in the training, showing evidence of reach. Post-training evaluations indicated participants learned skills in suicide prevention. Self-efficacy in connecting around and assessing and responding to suicide concerns rose significantly for both clinical and non-clinical staff. Non-clinical staff who had lower ratings for self-efficacy before training showed the greatest gains post-training. The perception of transfer of learning to practice was high. Staff interview data aligned with quantitative findings. Taken together, these findings indicate that InPlace Learning is a feasible and acceptable approach to suicide prevention workforce education in youth services with a positive impact on educational outcomes for staff.

Incremental Online Object Learning in a Vehicular Radar-Vision Fusion Framework

In this paper, we propose an object learning system that incorporates sensory information from an automotive radar system and a video camera. The radar system provides coarse attention for the focus of visual analysis on relatively small areas within the image plane. The attended visual areas are coded and learned by a three-layer neural network utilizing what is called in-place learning: Each neuron is responsible for the learning of its own processing characteristics within the connected network environment, through inhibitory and excitatory connections with other neurons. The modeled bottom-up, lateral, and top-down connections in the network enable sensory sparse coding, unsupervised learning, and supervised learning to occur concurrently. This paper is applied to learn two types of encountered objects in multiple outdoor driving settings. Cross-validation results show that the overall recognition accuracy is above 95% for the radar-attended window images. In comparison with the uncoded representation and purely unsupervised learning (without top-down connection), the proposed network improves the overall recognition rate by 15.93% and 6.35%, respectively. The proposed system is also compared favorably with other learning algorithms. The result indicates that our learning system is the only one that is fit for incremental and online object learning in a real-time driving environment.

Dually Optimal Neuronal Layers: Lobe Component Analysis

Development imposes great challenges. Internal ldquocorticalrdquorepresentations must be autonomously generated from interactive experiences. The eventual quality of these developed representations is of course important. Additionally, learning must be as fast as possible-to quickly derive better representation from limited experiences. Those who achieve both of these will have competitive advantages. We present a cortex-inspired theory called lobe component analysis (LCA) guided by the aforementioned dual criteria. A lobe component represents a high concentration of probability density of the neuronal input space. We explain how lobe components can achieve a dual-spatiotemporal (ldquobestrdquo and ldquofastestrdquo)-optimality, through mathematical analysis, in which we describe how lobe components plasticity can be temporally scheduled to take into account the <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">history</i> of observations in the best possible way. This contrasts with using only the last observation in gradient-based adaptive learning algorithms. Since they are based on two cell-centered mechanisms-Hebbian learning and lateral inhibition-lobe components develop <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">in-place</i> , meaning every networked neuron is individually responsible for the learning of its signal-processing characteristics within its connected network environment. There is no need for a separate learning network. We argue that in-place learning algorithms will be crucial for real-world large-size developmental applications due to their simplicity, low computational complexity, and generality. Our experimental results show that the learning speed of the LCA algorithm is drastically faster than other Hebbian-based updating methods and independent component analysis algorithms, thanks to its dual optimality, and it does not need to use any second- or higher order statistics. We also introduce the new principle of fast learning from stable representation.

FINDING PASSABLE REGIONS FOR ROBOTS FROM A SINGLE STILL IMAGE

Vision-guided obstacle avoidance, especially in unstructured environments, is a challenging issue in robotics. The paper proposes a biological inspired method to find passable regions based on the estimation of relative depth in a single still colour image. In the method, Multiple-layer In-place Learning Network (MILN) is applied to learn the passable regions in images, choosing several depth-related features extracted from the images as inputs. The method proposed here does not need any special prior knowledge or assumptions. We test our method on practical images of different scenes. Experimental results validate our method.

Hyposensitivity to the amnesic effects of scopolamine or amyloid β 25–35 peptide in heterozygous acetylcholinesterase knockout (AChE +/−) mice

We examined the sensitivity of AChE +/− mice to the amnesic effects of scopolamine and amyloid β peptide. AChE +/− and AChE +/+ littermates, tested at 5–9 weeks of age, failed to show any difference in locomotion, exploration and anxiety in the open-field test, or in-place learning in the water-maze. However, when treated with the muscarinic receptor antagonist scopolamine (0.5, 5 mg/kg s.c.) 20 min before each water-maze training session, learning impairments were observed at both doses in AChE +/+ mice, but only at the highest dose in AChE +/− mice. The central injection of Aβ 25–35 peptide (9 nmol) induced learning deficits only in AChE +/+ but not in AChE +/− mice. Therefore, the hyper-activity of cholinergic systems in AChE +/− mice did not result in increased memory abilities, but prevented the deleterious effects of muscarinic blockade or amyloid toxicity.

2008 Special Issue

Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By ''general-purpose'' we mean a general yet adaptive high-dimensional function app...

Multilayer in-place learning networks for modeling functional layers in the laminar cortex

Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By "general-purpose" we mean a general yet adaptive high-dimensional function approximator. In-place learning is a biological concept rooted in the genomic equivalence principle, meaning that each neuron is fully responsible for its own learning in its environment and there is no need for an external learner. Presented in this paper is the Multilayer In-place Learning Network (MILN) for this ambitious goal. Computationally, in-place learning provides unusually efficient learning algorithms whose simplicity, low computational complexity, and generality are set apart from typical conventional learning algorithms. Based on the neuroscience literature, we model the layer 4 and layer 2/3 as the feature layers in the 6-layer laminar cortex, with layer 4 using unsupervised learning and layer 2/3 using supervised learning. As a necessary requirement for autonomous mental development, MILN generates invariant neurons in different layers, with increasing invariance from earlier to later layers and the total invariance in the last motor layer. Such self-generated invariant representation is enabled mainly by descending (top-down) connections. The self-generated invariant representation is used as intermediate representations for learning later tasks in open-ended development.

A MULTILAYER IN-PLACE LEARNING NETWORK FOR DEVELOPMENT OF GENERAL INVARIANCES

Currently, there is a lack of general-purpose, in-place learning engines that incrementally learn multiple tasks, to develop "soft" multi-task-shared invariances in the intermediate internal representation while a developmental robot interacts with its environment. In-place learning is a biologically inspired concept, rooted in the genomic equivalence principle, meaning that each neuron is responsible for its own development while interacting with its environment. With in-place learning, there is no need for a separate learning network. Computationally, biologically inspired, in-place learning provides unusually efficient learning algorithms whose simplicity, low computational complexity, and generality are set apart from typical conventional learning algorithms. We present in this paper the multiple-layer in-place learning network (MILN) for this ambitious goal. As a key requirement for autonomous mental development, the network enables both unsupervised and supervised learning to occur concurrently, depending on whether motor supervision signals are available or not at the motor end (the last layer) during the agent's interactions with the environment. We present principles based on which MILN automatically develops invariant neurons in different layers and why such invariant neuronal clusters are important for learning later tasks in open-ended development. From sequentially sensed sensory streams, the proposed MILN incrementally develops a hierarchy of internal representations. The global invariance achieved through multi-layer invariances, with increasing invariance from early layers to the later layers. Experimental results with statistical performance measures are presented to show the effects of the principles.