Subcapital osteotomy of the first metatarsal is used as the treatment of choice for the correction
of hallux valgus. The advantages are a short operation time, no soft tissue procedures, …

Conventional neuro-computing architectures and artificial neural networks have often been
developed with no or loose connections to neuroscience. As a consequence, they have …

In this paper, we discuss the nonlinear computational power provided by dendrites in biological
and artificial neurons. We start by briefly presenting biological evidence about the type of …

… If the rank of this matrix M has a value r < m , then this value r can still be viewed as a
measure for the computational performance of this circuit C , since r is the number of “degrees of …

… We observe that in the sparse architecture discovered by DEEP R, the connectivity onto the
readout neurons Y is denser than in the rest of the network (see Fig. 1C). Detailed results are …

In an increasingly data-rich world the need for developing computing systems that cannot only
process, but ideally also interpret big data is becoming continuously more pressing. Brain-…

… This term is multiplied in the synaptic plasticity rule with the reward prediction error δ t = r t
+ γV t+1 − V t , where r t is the reward received at time t. This yields an instantaneous weight …

… In collaborative filtering, the system infers a model from all available data in R. One … The
blending algorithm is formally a function Ω : RF ↦→ R. The input x is a vector of individual …

… ε r as defined in Equation 29, whereas for we used ε r − = −ε r (note that the integral over ε …
r (r)≥0 for r>0 and ε r (r) = 0 for r<0 (also, f c (r) and ε r (r) must not be identical to zero for all r). …

… , DEEP R, that enables us to train directly a sparsely connected neural network. DEEP R …
We demonstrate that DEEP R can be used to train very sparse feedforward and recurrent …