Abstract
Previously, we have put forth the concept of Cartesian abstraction and argued that it can yield ‘cognitive maps’. We suggested a general mechanism and presented deep learning based numerical simulations: an observed factor (head direction) was non-linearly projected to form a discretized representation (head direction cells). That representation, in turn, enabled the development of a complementing factor (place cells) from high dimensional (visual) inputs. It has been shown that a related metric, in the form of oriented hexagonal grids, may also be derived. Elements of the algorithms were connected to the entorhinal-hippocampal complex (EHC loop). Here, we make one step further in the mapping to the neural substrate. We consider (i) the features of signals arriving at deep and superficial CA1 pyramidal cells, (ii) the interplay between lateral and medial entorhinal cortex efferents, and the nature of ‘instructive’ input timing-dependent plasticity, a feature of the loop. We suggest that the circuitry corresponds to a special form of Residual Networks that we call Sparsified and Twisted Residual Autoencoder (ST-RAE). We argue that ST-RAEs can learn Cartesian Factors and fit the structure and the working of the entorhinal-hippocampal complex to a reasonable extent, including certain oscillatory properties. We put forth the idea that the factor learning architecture of ST-RAEs has a double role in serving goal-oriented behavior, such as (a) the lowering the dimensionality of the task and (b) the mitigation of the problem of partial observation.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Scoville WB, Milner B (1957) Loss of recent memory after bilateral hippocampal lesions. J Neurol Neurosurg Psychiatry 20:11–21
Cohen NJ, Squire LR (1980) Preserved learning and retention of pattern analyzing skill in amnesia: dissociation of knowing how and knowing that. Science 210:207–210
O’Keefe J, Dostrovsky J (1971) The hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving rat. Brain Res 34:171–175
Knowlton BJ, Squire LR (1993) The learning of categories: parallel brain systems for item memory and category knowledge. Science 262(5140):1747–1749
Lavenex P, Lavenex PB, Amaral DG (2007) Spatial relational learning persists following neonatal hippocampal lesions in macaque monkeys. Nat Neurosci 10(2):234
Moser EI, Kropff E, Moser MB (2008) Place cells, grid cells, and the brain’s spatial representation system. Annu Rev Neurosci 31:69–89
Yartsev MM, Ulanovsky N (2013) Representation of three-dimensional space in the hippocampus of flying bats. Science 340(6130):367–372
Constantinescu AO, O’Reilly JX, Behrens TE (2016) Organizing conceptual knowledge in humans with a gridlike code. Science 352(6292):1464–1468
Lőrincz A (2016) Cartesian abstraction can yield ‘cognitive maps’. Procedia Comput Sci 88:259–271
Lőrincz A, Sárkány A (2017) Semi-supervised learning of cartesian factors: a top-down model of the entorhinal hippocampal complex. Front Psychol 8:215
Banino A, Barry C, Uria B, Blundell C, Lillicrap T, Mirowski P, Wayne G, Pritzel A, Chadwick MJ, Degris T, Modayil J, Wayne G, Soyer H, Viola F, Zhang B, Goroshin N, Rabinowitz N, Pascanu R, Beattie C, Petersen S, Sadik A, Gaffney S, King H, Kavukcuoglu K, Hassabis D, Hadsell R, Kumaran D (2018) Vector-based navigation using grid-like representations in artificial agents. Nature 557(7705):429–433
Garg R, Kumar VBG, Carneiro G, Reid I (2016) Unsupervised CNN for single view depth estimation: Geometry to the rescue. In: European conference on computer vision. Springer, Cham, pp 740–756
Godard C, Mac Aodha O, Brostow GJ (2017) Unsupervised monocular depth estimation with left-right consistency. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 270–279
Lőrincz A, Buzsáki G (2000) Two-phase computational model training long-term memories in the entorhinal-hippocampal region. Ann N Y Acad Sci 911(1):83–111
Chrobak JJ, Lőrincz A, Buzsáki G (2000) Physiological patterns in the hippocampo-entorhinal cortex system. Hippocampus 10(4):457–465
Lőrincz A, Szirtes G (2009) Here and now: how time segments may become events in the hippocampus. Neural Netw 22(5–6):738–747
Jaeger H (2002) Tutorial on training recurrent neural networks, covering BPPT, RTRL, EKF and the “echo state network” approach, vol 5. GMD-Forschungszentrum Informationstechnik, Bonn
Maass W, Natschläger T, Markram H (2002) Real-time computing without stable states: a new framework for neural computation based on perturbations. Neural Comput 14(11):2531–2560
Szita I, Gyenes V, Lőrincz A (2006) Reinforcement learning with echo state networks. In: International conference on artificial neural networks. Springer, Heidelberg, pp 830–839
Johnson MG, Hudson EL (1988) A variable delay line PLL for CPU-coprocessor synchronization. IEEE J Solid-State Circuits 23(5):1218–1223
Lőrincz A (1998) Forming independent components via temporal locking of reconstruction architectures: a functional model of the hippocampus. Biol Cybern 79(3):263–275
Markram H, Gerstner W, Sjöström PJ (2012) Spike-timing-dependent plasticity: a comprehensive overview. Front Synaptic Neurosci 4:2
Dudman JT, Tsay D, Siegelbaum SA (2007) A role for synaptic inputs at distal dendrites: instructive signals for hippocampal long-term plasticity. Neuron 56(5):866–879
Basu J, Zaremba JD, Cheung SK, Hitti FL, Zemelman BV, Losonczy A, Siegelbaum SA (2016) Gating of hippocampal activity, plasticity and memory by entorhinal cortex long-range inhibition. Science 351(6269):aaa5694
Mizuseki K, Diba K, Pastalkova E, Buzsáki G (2011) Hippocampal CA1 pyramidal cells form functionally distinct sublayers. Nat Neurosci 14(9):1174
Valero M, de la Prida LM (2018) The hippocampus in depth: a sublayer-specific perspective of entorhinal–hippocampal function. Curr Opin Neurobiol 52:107–114
Sanders H, Ji D, Sasaki T, Leutgeb JK, Wilson MA, Lisman JE (2019) Temporal coding and rate remapping: representation of nonspatial information in the hippocampus. Hippocampus 29(2):111–127
Herzog LE, Pascual LM, Scott SJ, Mathieson ER, Katz DB, Jadhav SP (2019) Interaction of taste and place coding in the hippocampus. J Neurosci 39(16):3057–3069
Szita I, Lorincz A (2008) Factored value iteration converges. Acta Cybern 18(4):615–635
Szita I, Lőrincz A (2009) Optimistic initialization and greediness lead to polynomial time learning in factored MDPs. In: Proceedings of the 26th annual int. conf on machine learning. ACM, pp 1001–1008
Miller R (1989) Cortico-hippocampal interplay: self-organizing phase-locked loops for indexing memory. Psychobiology 17(2):115–128
Acknowledgments
The research has been supported by the European Union, co-financed by the European Social Fund (EFOP-3.6.3-VEKOP-16-2017-00002) and by the ELTE Institutional Excellence Program (1783-3/2018/FEKUTSRAT) supported by the Hungarian Ministry of Human Capacities.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Lőrincz, A. (2020). Sparsified and Twisted Residual Autoencoders. In: Samsonovich, A. (eds) Biologically Inspired Cognitive Architectures 2019. BICA 2019. Advances in Intelligent Systems and Computing, vol 948. Springer, Cham. https://doi.org/10.1007/978-3-030-25719-4_41
Download citation
DOI: https://doi.org/10.1007/978-3-030-25719-4_41
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-25718-7
Online ISBN: 978-3-030-25719-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)