S. Tiwari

N. K. Mahato, A. Klar, S. Tiwari

In this paper we present numerical simulations of a macroscopic vision-based model [1] derived from microscopic situation rules described in [2]. This model describes an approach to collision avoidance between pedestrians by taking decisions of turning or slowing down based on basic interaction rules, where the dangerousness level of an interaction with another pedestrian is measured in terms of the derivative of the bearing angle and of the time-to-interaction. A meshfree particle method is used to solve the equations of the model. Several numerical cases are considered to compare this model with models established in the field, for example, social force model coupled to an Eikonal equation [3]. Particular emphasis is put on the comparison of evacuation and computation times. References 1. Degond P., Appert-Rolland C., Pettere J., Theraulaz G., Vision-based macroscopic pedestrian models, Kinetic and Related models, AIMs 6(4), 809-839 (2013) 2. Ondrej J., Pettere J., Olivier A.H., Donikian S., A synthetic-vision based steering approach for crowd simulation, ACM Transactions on Graphics, 29(4), Article 123 (2010) 3. Etikyala R., Gottlich S., Klar A., Tiwari S., Particle methods for pedestrian flow models: From microscopic to nonlocal continuum models, Mathematical Models and Methods in Applied Sciences, 20(12), 2503-2523 (2014)

S. Tiwari, M. Gogoi, S. Verma et al.

Optimization-based meta-learning aims to learn an initialization so that a new unseen task can be learned within a few gradient updates. Model Agnostic Meta-Learning (MAML) is a benchmark algorithm comprising two optimization loops. The inner loop is dedicated to learning a new task and the outer loop leads to meta-initialization. However, ANIL (almost no inner loop) algorithm shows that feature reuse is an alternative to rapid learning in MAML. Thus, the meta-initialization phase makes MAML primed for feature reuse and obviates the need for rapid learning. Contrary to ANIL, we hypothesize that there may be a need to learn new features during meta-testing. A new unseen task from non-similar distribution would necessitate rapid learning in addition reuse and recombination of existing features. In this paper, we invoke the width-depth duality of neural networks, wherein, we increase the width of the network by adding extra computational units (ACU). The ACUs enable the learning of new atomic features in the meta-testing task, and the associated increased width facilitates information propagation in the forwarding pass. The newly learnt features combine with existing features in the last layer for meta-learning. Experimental results show that our proposed MAC method outperformed existing ANIL algorithm for non-similar task distribution by approximately 13% (5-shot task setting)