activity
20162020
most citedAn Integer Programming Approach to Deep Neural Networks with Binary Activation Functions

8 citations · 8 across the 2 of their papers we have counts for

collaborators

8 papers

cs.CV2020

Towards the Localisation of Lesions in Diabetic Retinopathy

Samuel Ofosu Mensah, Bubacarr Bah, Willie Brink

Convolutional Neural Networks (CNNs) have successfully been used to classify diabetic retinopathy (DR) fundus images in recent times. However, deeper representations in CNNs may ca…

math.OC20208 cited

An Integer Programming Approach to Deep Neural Networks with Binary Activation Functions

Bubacarr Bah, Jannis Kurtz

We study deep neural networks with binary activation functions (BDNN), i.e. the activation function only has two states. We show that the BDNN can be reformulated as a mixed-intege…

cs.LG2020

On Error Correction Neural Networks for Economic Forecasting

Mhlasakululeka Mvubu, Emmanuel Kabuga, Christian Plitz +3

Recurrent neural networks (RNNs) are more suitable for learning non-linear dependencies in dynamical systems from observed time series data. In practice all the external variables…

cs.IT2020

Efficient Tuning-Free -Regression of Nonnegative Compressible Signals

Hendrik Bernd Petersen, Bubacarr Bah, Peter Jung

In compressed sensing the goal is to recover a signal from as few as possible noisy, linear measurements. The general assumption is that the signal has only a few non-zero entries.…

math.OC2019

Learning deep linear neural networks: Riemannian gradient flows and convergence to global minimizers

Bubacarr Bah, Holger Rauhut, Ulrich Terstiege +1

We study the convergence of gradient flows related to learning deep linear neural networks (where the activation function is the identity map) from data. In this case, the composit…

math.OC2019

Discrete Optimization Methods for Group Model Selection in Compressed Sensing

Bubacarr Bah, Jannis Kurtz, Oliver Schaudt

In this article we study the problem of signal recovery for group models. More precisely for a given set of groups, each containing a small subset of indices, and for given linear…