Related papers: Pavlov's dog associative learning demonstrated on …
Memristive devices are commonly benchmarked by the multi-level programmability of their resistance states. Neural networks utilizing memristor crossbar arrays as synaptic layers largely rely on this feature. However, the dynamical…
Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the…
Reproducing the diverse and agile locomotion skills of animals has been a longstanding challenge in robotics. While manually-designed controllers have been able to emulate many complex behaviors, building such controllers involves a…
Neuromorphic computing which aims to mimic the collective and emergent behavior of the brain's neurons, synapses, axons, dendrites offers an intriguing, potentially disruptive solution to society's ever-growing computational needs. Although…
The story of information processing is a story of great success. Todays' microprocessors are devices of unprecedented complexity and MOSFET transistors are considered as the most widely produced artifact in the history of mankind. The…
Computation on a large volume of data at high speed and low power requires energy-efficient computing architectures. Spiking neural network (SNN) with bio-inspired spike-timing-dependent plasticity learning (STDP) is a promising solution…
Biological neural networks are characterized by their high degree of plasticity, a core property that enables the remarkable adaptability of natural organisms. Importantly, this ability affects both the synaptic strength and the topology of…
Nanoscale resistive memories are expected to fuel dense integration of electronic synapses for large-scale neuromorphic system. To realize such a brain-inspired computing chip, a compact CMOS spiking neuron that performs in-situ learning…
As the limits of traditional von Neumann computing come into view, the brain's ability to communicate vast quantities of information using low-power spikes has become an increasing source of inspiration for alternative architectures. Key to…
Pomsets are a promising formalism for concurrent programs based on partially ordered sets. Among this class, series-parallel pomsets admit a convenient linear representation and can be recognized by simple algebraic structures known as…
Hardware neural networks could perform certain computational tasks orders of magnitude more energy-efficiently than conventional computers. Artificial neurons are a key component of these networks and are currently implemented with…
In this project we trained a neural network to perform specific interactions between a robot and objects in the environment, through imitation learning. In particular, we tackle the task of moving the robot to a fixed pose with respect to a…
Hopfield neural networks are a possible basis for modelling associative memory in living organisms. After summarising previous studies in the field, we take a new look at learning rules, exhibiting them as descent-type algorithms for…
Simulating interactions between non-spherical colloidal particles is computationally challenging due to the complex dependency of forces and energies on their geometry. We introduce and evaluate both descriptor-based and end-to-end models…
One of the challenges of modern neuroscience is creating a "living computer" based on neural networks grown in vitro. Such an artificial device is supposed to perform neurocomputational tasks and interact with the environment when embodied…
Nature inspired neuromorphic architectures are being explored as an alternative to imminent limitations of conventional complementary metal-oxide semiconductor (CMOS) architectures. Utilization of such architectures for practical…
Memristors have been widely studied as artificial synapses in neuromorphic circuits, due to their functional similarity with biological synapses, low operating power, and high integration density. In this work, a memristive synapse,…
We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the imposed structure can be leveraged upstream. In particular, we control the connectivity of an…
Brain-inspired learning in physical hardware has enormous potential to learn fast at minimal energy expenditure. One of the characteristics of biological learning systems is their ability to learn in the presence of various noise sources.…
We report a detailed study of neuromorphic switching behaviour in inherently complex percolating networks of self-assembled metal nanoparticles. We show that variation of the strength and duration of the electric field applied to this…