Search Results for author:
Found 10 papers, 4 papers with code
Efficient optimization of ODE neuron models using gradient descent
Differentiable neuron models, which should be added to popular neuron simulation packages, promise a new era of optimizable neuron models with many free parameters, a key feature of real neurons.
Learning domain-specific causal discovery from time series
Causal discovery (CD) from time-varying data is important in neuroscience, medicine, and machine learning.
Nothing makes sense in deep learning, except in the light of evolution
These deconstraints can be very helpful to both the particular algorithm in how it handles challenges in implementation and the overall field of DL in how easy it is for new ideas to be generated.
Do biological constraints impair dendritic computation?
Computations on the dendritic trees of neurons have important constraints.
Can Single Neurons Solve MNIST? The Computational Power of Biological Dendritic Trees
If dendritic trees can be nonlinear, biological neurons may have far more computational power than their artificial counterparts.
Neurons and Cognition
PDE constraints on smooth hierarchical functions computed by neural networks
Our approach is a step toward formulating an algebraic description of functional spaces associated with specific neural networks, and may provide new, useful tools for constructing neural networks.
Learning to solve the credit assignment problem
We provide proof that our approach converges to the true gradient for certain classes of networks.
On functions computed on trees
Any function can be constructed using a hierarchy of simpler functions through compositions.
Towards learning-to-learn
Yet, in analogy with GOFAI, there is no reason to believe that humans are particularly good at defining such learning systems: we may expect learning itself to be better if we learn it.
Efficient Multi-Person Pose Estimation with Provable Guarantees
We test our approach on the MPII-Multiperson dataset, showing that our approach obtains comparable results with the state-of-the-art algorithm for joint node labeling and grouping problems, and that NBD achieves considerable speed-ups relative to a naive dynamic programming approach.
