Search

Spatio-temporal pattern recognition is a fundamental ability of the brain which is required for numerous real-world activities. Recent deep learning approaches have reached outstanding accuracies in such tasks, but their implementation on conventional embedded solutions is still very computationally and energy expensive. Tactile sensing in robotic applications is a representative example where real-time processing and energy efficiency are required. Following a brain-inspired computing approach, we propose a new benchmark for spatio-temporal tactile pattern recognition at the edge through Braille letter reading. We recorded a new Braille letters dataset based on the capacitive tactile sensors of the iCub robot's fingertip. We then investigated the importance of spatial and temporal information as well as the impact of event-based encoding on spike-based computation. Afterward, we trained and compared feedforward and recurrent Spiking Neural Networks (SNNs) offline using Backpropagation Through Time (BPTT) with surrogate gradients, then we deployed them on the Intel Loihi neuromorphic chip for fast and efficient inference. We compared our approach to standard classifiers, in particular to the Long Short-Term Memory (LSTM) deployed on the embedded NVIDIA Jetson GPU, in terms of classification accuracy, power, and energy consumption together with computational delay. Our results show that the LSTM reaches ~97% of accuracy, outperforming the recurrent SNN by ~17% when using continuous frame-based data instead of event-based inputs. However, the recurrent SNN on Loihi with event-based inputs is ~500 times more energy-efficient than the LSTM on Jetson, requiring a total power of only ~30 mW. This work proposes a new benchmark for tactile sensing and highlights the challenges and opportunities of event-based encoding, neuromorphic hardware, and spike-based computing for spatio-temporal pattern recognition at the edge.

Discriminating distinct objects and concepts from sensory stimuli is essential for survival. Our brains accomplish this feat by forming disentangled internal representations in deep sensory networks shaped through experience-dependent synaptic plasticity. To elucidate the principles that underlie sensory representation learning, we derive a local plasticity model that shapes latent representations to predict future activity. This Latent Predictive Learning (LPL) rule conceptually extends Bienenstock-Cooper-Munro (BCM) theory by unifying Hebbian plasticity with predictive learning. We show that deep neural networks equipped with LPL develop disentangled object representations without supervision. The same rule accurately captures neuronal selectivity changes observed in the primate inferotemporal cortex in response to altered visual experience. Finally, our model generalizes to spiking neural networks and naturally accounts for several experimentally observed properties of synaptic plasticity, including metaplasticity and spike-timing-dependent plasticity (STDP). We thus provide a plausible normative theory of representation learning in the brain while making concrete testable predictions.

To rapidly process information, neural circuits have to amplify specific activity patterns transiently. How the brain performs this nonlinear operation remains elusive. Hebbian assemblies are one possibility whereby symmetric excitatory connections boost neuronal activity. However, such Hebbian amplification is often associated with dynamical slowing of network dynamics, non-transient attractor states, and pathological run-away activity. Feedback inhibition can alleviate these effects but typically linearizes responses and reduces amplification gain. At the same time, other alternative mechanisms rely on asymmetric connectivity, in conflict with the Hebbian doctrine. Here we propose nonlinear transient amplification (NTA), a plausible circuit mechanism that reconciles symmetric connectivity with rapid amplification while avoiding the above issues. NTA has two distinct temporal phases. Initially, positive feedback excitation selectively amplifies inputs that exceed a critical threshold. Subsequently, short-term plasticity quenches the run-away dynamics into an inhibition-stabilized network state. By characterizing NTA in supralinear network models, we establish that the resulting onset transients are stimulus selective and well-suited for speedy information processing. Further, we find that excitatory-inhibitory co-tuning widens the parameter regime in which NTA is possible. In summary, NTA provides a parsimonious explanation for how excitatory-inhibitory co-tuning and short-term plasticity collaborate in recurrent networks to achieve transient amplification.

Recent research resolves the challenging problem of building biophysically plausible spiking neural models that are also capable of complex information processing. This advance creates new opportunities in neuroscience and neuromorphic engineering, which we discussed at an online focus meeting. Recent research resolves the challenging problem of building biophysically plausible spiking neural models that are also capable of complex information processing. Zenke et al. report on a focus meeting discussing the opportunities created by this advance for neuroscience and neuromorphic engineering.

Brains process information in spiking neural networks. Their intricate connections shape the diverse functions these networks perform. Yet how network connectivity relates to function is poorly understood, and the functional capabilities of models of spiking networks are still rudimentary. The lack of both theoretical insight and practical algorithms to find the necessary connectivity poses a major impediment to both studying information processing in the brain and building efficient neuromorphic hardware systems. The training algorithms that solve this problem for artificial neural networks typically rely on gradient descent. But doing so in spiking networks has remained challenging due to the nondifferentiable nonlinearity of spikes. To avoid this issue, one can employ surrogate gradients to discover the required connectivity. However, the choice of a surrogate is not unique, raising the question of how its implementation influences the effectiveness of the method. Here, we use numerical simulations to systematically study how essential design parameters of surrogate gradients affect learning performance on a range of classification problems. We show that surrogate gradient learning is robust to different shapes of underlying surrogate derivatives, but the choice of the derivative's scale can substantially affect learning performance. When we combine surrogate gradients with suitable activity regularization techniques, spiking networks perform robust information processing at the sparse activity limit. Our study provides a systematic account of the remarkable robustness of surrogate gradient learning and serves as a practical guide to model functional spiking neural networks.

Key points During the computation of sound localization, neurons of the lateral superior olive (LSO) integrate synaptic excitation arising from the ipsilateral ear with inhibition from the contralateral ear. We characterized the functional connectivity of the inhibitory and excitatory inputs onto LSO neurons in terms of unitary synaptic strength and convergence. Unitary IPSCs can generate large conductances, although their strength varies over a 10-fold range in a given recording. By contrast, excitatory inputs are relatively weak. The conductance associated with IPSPs needs to be at least 2-fold stronger than the excitatory one to guarantee effective inhibition of action potential (AP) firing. Computational modelling showed that strong unitary inhibition ensures an appropriate slope and midpoint of the tuning curve of LSO neurons. Conversely, weak but numerous excitatory inputs filter out spontaneous AP firing from upstream auditory neurons. Abstract The lateral superior olive (LSO) is a binaural nucleus in the auditory brainstem in which excitation from the ipsilateral ear is integrated with inhibition from the contralateral ear. It is unknown whether the strength of the unitary inhibitory and excitatory inputs is adapted to allow for optimal tuning curves of LSO neuron action potential (AP) firing. Using electrical and optogenetic stimulation of afferent synapses, we found that the strength of unitary inhibitory inputs to a given LSO neuron can vary over a ∼10-fold range, follows a roughly log-normal distribution, and, on average, causes a large conductance (9 nS). Conversely, unitary excitatory inputs, stimulated optogenetically under the bushy-cell specific promoter Math5, were numerous, and each caused a small conductance change (0.7 nS). Approximately five to seven bushy cell inputs had to be active simultaneously to bring an LSO neuron to fire. In double stimulation experiments, the effective inhibition window caused by IPSPs was short (1-3 ms) and its length depended on the inhibitory conductance; an ∼2-fold stronger inhibition than excitation was needed to suppress AP firing. Computational modelling suggests that few, but strong, unitary IPSPs create a tuning curve of LSO neuron firing with an appropriate slope and midpoint. Furthermore, weak but numerous excitatory inputs reduce the spontaneous AP firing that LSO neurons would otherwise inherit from their upstream auditory neurons. Thus, the specific connectivity and strength of unitary excitatory and inhibitory inputs to LSO neurons is optimized for the computations performed by these binaural neurons.

Hebbian plasticity, a synaptic mechanism which detects and amplifies co-activity between neurons, is considered a key ingredient underlying learning and memory in the brain. However, Hebbian plasticity alone is unstable, leading to runaway neuronal activity, and therefore requires stabilization by additional compensatory processes. Traditionally, a diversity of homeostatic plasticity phenomena found in neural circuits are thought to play this role. However, recent modelling work suggests that the slow evolution of homeostatic plasticity, as observed in experiments, is insufficient to prevent instabilities originating from Hebbian plasticity. To remedy this situation, we suggest that homeostatic plasticity is complemented by additional rapid compensatory processes, which rapidly stabilize neuronal activity on short timescales.

Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In the case of artificial neural networks, the three components specified by design are the objective functions, the learning rules, and architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.

Synaptic plasticity, a key process for memory formation, manifests itself across different time scales ranging from a few seconds for plasticity induction up to hours or even years for consolidation and memory retention. We developed a three-layered model of synaptic consolidation that accounts for data across a large range of experimental conditions. Consolidation occurs in the model through the interaction of the synaptic efficacy with a scaffolding variable by a read-write process mediated by a tagging-related variable. Plasticity-inducing stimuli modify the efficacy, but the state of tag and scaffold can only change if a write protection mechanism is overcome. Our model makes a link from depotentiation protocolsin vitroto behavioral results regarding the influence of novelty on inhibitory avoidance memory in rats.

In a search for $\omega$ mesic states, the production of $\omega$-mesons in coincidence with forward going protons has been studied in photon induced reactions on $^{12}$C for incident photon energies of 1250 - 3100 MeV. The $\pi^0 \gamma$ pairs from decays of bound or quasi-free $\omega$-mesons have been measured with the CBELSA/TAPS detector system in coincidence with protons registered in the MiniTAPS forward array. Structures in the total energy distribution of the $\pi^0 \gamma$ pairs, which would indicate the population and decay of bound $\omega~^{11}$B states, are not observed. The $\pi^0 \gamma$ cross section of 0.3 nb/MeV/sr observed in the bound state energy regime between -100 and 0 MeV may be accounted for by yield leaking into the bound state regime because of the large in-medium width of the $\omega$-meson. A comparison of the measured total energy distribution with calculations suggests the real part $V_0$ of the $\omega~^{11}$B potential to be small and only weakly attractive with $V_0(\rho=\rho_0) = -15\pm$ 35(stat) $\pm$20(syst) MeV in contrast to some theoretical predictions of attractive potentials with a depth of 100 - 150 MeV., Comment: 13 pages, 8 figures