Genetic programming is an optimization algorithm inspired by natural selection which automatically evolves the structure of computer programs. The resulting computer programs are interpretable and efficient compared to black-box models with fixed structure. The fitness evaluation in genetic programming suffers from high computational requirements, limiting the performance on difficult problems. To reduce the runtime, many implementations of genetic programming require a specific data format, making the applicability limited to specific problem classes. Consequently, there is no efficient genetic programming framework that is usable for a wide range of tasks. To this end, we developed Kozax, a genetic programming framework that evolves symbolic expressions for arbitrary problems. We implemented Kozax using JAX, a framework for high-performance and scalable machine learning, which allows the fitness evaluation to scale efficiently to large populations or datasets on GPU. Furthermore, Kozax offers constant optimization, custom operator definition and simultaneous evolution of multiple trees. We demonstrate successful applications of Kozax to discover equations of natural laws, recover equations of hidden dynamic variables and evolve a control policy. Overall, Kozax provides a general, fast, and scalable library to optimize white-box solutions in the realm of scientific computing.

Traditional backpropagation of error, though a highly successful algorithm for learning in artificial neural network models, includes features which are biologically implausible for learning in real neural circuits. An alternative called target propagation proposes to solve this implausibility by using a top-down model of neural activity to convert an error at the output of a neural network into layer-wise and plausible 'targets' for every unit. These targets can then be used to produce weight updates for network training. However, thus far, target propagation has been heuristically proposed without demonstrable equivalence to backpropagation. Here, we derive an exact correspondence between backpropagation and a modified form of target propagation (GAIT-prop) where the target is a small perturbation of the forward pass. Specifically, backpropagation and GAIT-prop give identical updates when synaptic weight matrices are orthogonal. In a series of simple computer vision experiments, we show near-identical performance between backpropagation and GAIT-prop with a soft orthogonality-inducing regularizer.

In this paper we introduce the temporally factorized 3D convolution (3TConv) as an interpretable alternative to the regular 3D convolution (3DConv). In a 3TConv the 3D convolutional filter is obtained by learning a 2D filter and a set of temporal transformation parameters, resulting in a sparse filter where the 2D slices are sequentially dependent on each other in the temporal dimension. We demonstrate that 3TConv learns temporal transformations that afford a direct interpretation. The temporal parameters can be used in combination with various existing 2D visualization methods. We also show that insight about what the model learns can be achieved by analyzing the transformation parameter statistics on a layer and model level. Finally, we implicitly demonstrate that, in popular ConvNets, the 2DConv can be replaced with a 3TConv and that the weights can be transferred to yield pretrained 3TConvs.

The de facto standard for causal inference is the randomized controlled trial, where one compares an manipulated group with a control group in order to determine the effect of an intervention. However, this research design is not always realistically possible due to pragmatic or ethical concerns. In these situations, quasi-experimental designs may provide a solution, as these allow for causal conclusions at the cost of additional design assumptions. In this paper, we provide a generic framework for quasi-experimental design using Bayesian model comparison, and we show how it can be used as an alternative to several common research designs. We provide a theoretical motivation for a Gaussian process based approach and demonstrate its convenient use in a number of simulations. Finally, we apply the framework to determine the effect of population-based thresholds for municipality funding in France, of the 2005 smoking ban in Sicily on the number of acute coronary events, and of the effect of an alleged historical phantom border in the Netherlands on Dutch voting behaviour.

In this paper we introduce a family of stochastic gradient estimation techniques based of the perturbative expansion around the mean of the sampling distribution. We characterize the bias and variance of the resulting Taylor-corrected estimators using the Lagrange error formula. Furthermore, we introduce a family of variance reduction techniques that can be applied to other gradient estimators. Finally, we show that these new perturbative methods can be extended to discrete functions using analytic continuation. Using this technique, we derive a new gradient descent method for training stochastic networks with binary weights. In our experiments, we show that the perturbative correction improves the convergence of stochastic variational inference both in the continuous and in the discrete case.

In this paper, we introduce a new form of amortized variational inference by using the forward KL divergence in a joint-contrastive variational loss. The resulting forward amortized variational inference is a likelihood-free method as its gradient can be sampled without bias and without requiring any evaluation of either the model joint distribution or its derivatives. We prove that our new variational loss is optimized by the exact posterior marginals in the fully factorized mean-field approximation, a property that is not shared with the more conventional reverse KL inference. Furthermore, we show that forward amortized inference can be easily marginalized over large families of latent variables in order to obtain a marginalized variational posterior. We consider two examples of variational marginalization. In our first example we train a Bayesian forecaster for predicting a simplified chaotic model of atmospheric convection. In the second example we train an amortized variational approximation of a Bayesian optimal classifier by marginalizing over the model space. The result is a powerful meta-classification network that can solve arbitrary classification problems without further training.

This paper introduces the kernel mixture network, a new method for nonparametric estimation of conditional probability densities using neural networks. We model arbitrarily complex conditional densities as linear combinations of a family of kernel functions centered at a subset of training points. The weights are determined by the outer layer of a deep neural network, trained by minimizing the negative log likelihood. This generalizes the popular quantized softmax approach, which can be seen as a kernel mixture network with square and non-overlapping kernels. We test the performance of our method on two important applications, namely Bayesian filtering and generative modeling. In the Bayesian filtering example, we show that the method can be used to filter complex nonlinear and non-Gaussian signals defined on manifolds. The resulting kernel mixture network filter outperforms both the quantized softmax filter and the extended Kalman filter in terms of model likelihood. Finally, our experiments on generative models show that, given the same architecture, the kernel mixture network leads to higher test set likelihood, less overfitting and more diversified and realistic generated samples than the quantized softmax approach.

Neural signals are characterized by rich temporal and spatiotemporal dynamics that reflect the organization of cortical networks. Theoretical research has shown how neural networks can operate at different dynamic ranges that correspond to specific types of information processing. Here we present a data analysis framework that uses a linearized model of these dynamic states in order to decompose the measured neural signal into a series of components that capture both rhythmic and non-rhythmic neural activity. The method is based on stochastic differential equations and Gaussian process regression. Through computer simulations and analysis of magnetoencephalographic data, we demonstrate the efficacy of the method in identifying meaningful modulations of oscillatory signals corrupted by structured temporal and spatiotemporal noise. These results suggest that the method is particularly suitable for the analysis and interpretation of complex temporal and spatiotemporal neural signals.

In magnetoencephalography (MEG) the conventional approach to source reconstruction is to solve the underdetermined inverse problem independently over time and space. Here we present how the conventional approach can be extended by regularizing the solution in space and time by a Gaussian process (Gaussian random field) model. Assuming a separable covariance function in space and time, the computational complexity of the proposed model becomes (without any further assumptions or restrictions) $\mathcal{O}(t^3 + n^3 + m^2n)$, where $t$ is the number of time steps, $m$ is the number of sources, and $n$ is the number of sensors. We apply the method to both simulated and empirical data, and demonstrate the efficiency and generality of our Bayesian source reconstruction approach which subsumes various classical approaches in the literature.