The ability to remember events plays an important role in hu-man life. People can replay past events in their heads and makedecisions based on that information. In this paper, we describea novel extension to a cognitive architecture, ICARUS, that en-ables it to store, organize, generalize, and retrieve episodictraces that can help the agent in a variety of manners. Af-ter discussing previous work on the related topic, we reviewICARUS and explain the new extension to the architecture indetail. Then we discuss four architectural implications of thenew capability and list some future work before we conclude.

Primate visual development is characterized by low visual acuity and colour sensitivity besides high plasticity and synapticgrowth in the first year of infancy, prior to the development of specific visual-cognitive functions. In this work, weinvestigate the possible synergy between the gradual variation in visual input distribution and the concurrent growth of astatistical model of vision on the task of large-scale object classification. We adopt deep convolutional neural networks(CNNs) as a statistical model of vision and study its performance in 4 training setups each varying in either the modelbeing static or growing in parameters or the visual input being fully-formed or refining in saturation, contrast and spatialresolution. Our experiments indicate that a setup reflective of infant visual development, wherein a gradually growingmodel is trained on a refining visual input distribution, converges to a better generalization at a faster rate in comparisonto other setups.