Abdul-Saboor Sheikh

Zalando SE · Research

Target prioritization is essential for drug discovery and repositioning. Applying computational methods to analyze and process multi-omics data to find new drug targets is a practical approach for achieving this. Despite an increasing number of methods for generating datasets such as genomics, phenomics, and proteomics, attempts to integrate and mi...

Time series forecasting is often fundamental to scientific and engineering problems and enables decision making. With ever increasing data set sizes, a trivial solution to scale up predictions is to assume independence between interacting time series. However, modeling statistical dependencies can improve accuracy and enable analysis of interaction...

ProSper is a python library containing probabilistic algorithms to learn dictionaries. Given a set of data points, the implemented algorithms seek to learn the elementary components that have generated the data. The library widens the scope of dictionary learning approaches beyond implementations of standard approaches such as ICA, NMF or standard...

ProSper is a python library containing probabilistic algorithms to learn dictionaries. Given a set of data points, the implemented algorithms seek to learn the elementary components that have generated the data. The library widens the scope of dictionary learning approaches beyond implementations of standard approaches such as ICA, NMF or standard...

Personalized size and fit recommendations bear crucial significance for any fashion e-commerce platform. Predicting the correct fit drives customer satisfaction and benefits the business by reducing costs incurred due to size-related returns. Traditional collaborative filtering algorithms seek to model customer preferences based on their previous o...

Deep Reinforcement Learning has been shown to be very successful in complex games, e.g. Atari or Go. These games have clearly defined rules, and hence allow simulation. In many practical applications, however, interactions with the environment are costly and a good simulator of the environment is not available. Further, as environments differ by ap...

We investigate how the neural processing in auditory cortex is shaped by the statistics of natural sounds. Hypothesising that auditory cortex (A1) represents the structural primitives out of which sounds are composed, we employ a statistical model to extract such components. The input to the model are cochleagrams which approximate the non-linear t...

600 most-frequently used generative and corresponding receptive field estimates obtained with the BSC model. 600 most-frequently used generative and corresponding receptive field estimates obtained with the BSC model. The fields are ordered w.r.t. their marginal posterior probability from left to right and top to bottom. (EPS)

Histogram of best spectral and temporal modulation frequencies for experimentally recorded STRFs and BSC model receptive fields. Histogram of best spectral and temporal modulation frequencies for all the 600 model receptive fields shown in S1 Fig (left) and S2 Fig (left), respectively. Model receptive fields were analyzed as in Fig 4 with the same...

Distribution over experimentally recorded and BSC model neurons of temporal and frequency tuning widths. A: Distribution over neurons of temporal tuning widths of excitatory fields of the real (pink) and BSC model (grey) neurons. B: Distribution of temporal tuning widths of inhibitory fields. C: Distribution of frequency tuning widths of excitatory...

STRF estimates of MCA can be found in this file. (MAT)

Generative fields and STRF estimates of the BSC model can be found in this file. (MAT)

Details about the Methods and Results sections can be found in this file. (PDF)

STRF estimates based on measurements in A1 of ferrets can be found in this file. (MAT)

Measuring tuning width. Measuring tuning width for Fig 5. A: To measure frequency tuning width for the excitatory part of the STRF first an STRF is taken. B: Then STRF is element-wise positively rectified and then squared. C: Finally the rectified squared STRF is summed over time, and the (not necessarily contiguous) span above half the height is m...

File descriptions and Matlab code can be found in this file. (TXT)

MCA generative fields can be found in this file. (MAT)

600 most-frequently used generative and corresponding receptive field estimates obtained with the MCA model. 600 most-frequently used generative and corresponding receptive field estimates obtained with the MCA model. The fields are ordered w.r.t. their marginal posterior probability from left to right and top to bottom. (EPS)

We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion. Our approach jointly models a size purchased by a customer, and its possible return event: 1. no return, 2. returned too small 3. returned too big. Those events are drawn following a multinomial distribution parameterized on...

We introduce a hierarchical Bayesian approach to tackle the challenging problem of size recommendation in e-commerce fashion. Our approach jointly models a size purchased by a customer, and its possible return event: 1. no return, 2. returned too small 3. returned too big. Those events are drawn following a multinomial distribution parameterized on...

We explore classifier training for data sets with very few labels. We investigate this task using a neural network for nonnegative data. The network is derived from a hierarchical normalized Poisson mixture model with one observed and two hidden layers. With the single objective of likelihood optimization, both labeled and unlabeled data are natura...

This work explores maximum likelihood optimization of neural networks through hypernetworks. A hypernetwork initializes the weights of another network, which in turn can be employed for typical functional tasks such as regression and classification. We optimize hypernetworks to directly maximize the conditional likelihood of target variables given...

Probabilistic inference serves as a popular model for neural processing. It is still unclear, however, how approximate probabilistic inference can be accurate and scalable to very high-dimensional continuous latent spaces. Especially as typical posteriors for sensory data can be expected to exhibit complex latent dependencies including multiple mod...

Deep learning is intensively studied from both the perspectives of unsupervised and supervised learning approaches. The combination of the two learning schemes is typically done using separate algorithms, often resulting in complex and heterogeneous systems that are equipped with large numbers of tunable parameters. In this work we study the potent...

Sparse coding is a popular approach to model natural images but has faced two main challenges: modelling low-level image components (such as edge-like structures and their occlusions) and modelling varying pixel intensities. Traditionally, images are modelled as a sparse linear superposition of dictionary elements, where the probabilistic view of t...

Modelling natural images with sparse coding (SC) has faced two main challenges: flexibly representing varying pixel intensities and realistically representing low-level image components. This paper proposes a novel multiple-cause generative model of low-level image statistics that generalizes the standard SC model in two crucial points: (1) it uses...

We study inference and learning based on a sparse coding model with `spike-and-slab' prior. As standard sparse coding, the used model assumes independent latent sources that linearly combine to generate data points. However, instead of using a standard sparse prior such as a Laplace distribution, we study the application of a more flexible `spike-a...

We define and discuss the first sparse coding algorithm based on closed-form EM updates and continuous latent variables. The underlying generative model consists of a standard `spike-and-slab' prior and a Gaussian noise model. Closed-form solutions for E- and M-step equations are derived by generalizing probabilistic PCA. The resulting EM algorithm...

Neural activity encodes multiple-cause stimuli with discrete events. Neurons either spike or remain inactive. Many modeling approaches therefore rely on binary units for encoding. Prominent examples are, for instance, restricted Boltzmann machines and, more recently, deep belief networks. In this work we study a probabilistic generative model with...

An increasing number of experimental studies indicate that perception encodes a posterior probability distribution over possible causes of sensory stimuli, which is used to act close to optimally in the environment. One outstanding difficulty with this hypothesis is that the exact posterior will in general be too complex to be represented directly,...

A method and framework are described for detecting changes in a multivariate data stream. A training set is formed by sampling time windows in a data stream containing data reflecting normal conditions. A histogram is created to summarize each window of data, and data within the histograms are clustered to form test distribution representatives to...

The SLIF project combines text-mining and image processing to extract structured information from biomedical literature.SLIF extracts images and their captions from published papers. The captions are automatically parsed for relevant biological entities (protein and cell type names), while the images are classified according to their type (e.g., mi...

Slif uses a combination of text-mining and image processing to extract information from figures in the biomedical literature. It also uses innovative extensions to traditional latent topic modeling to provide new ways to traverse the literature. Slif provides a publicly available searchable database (http://slif.cbi.cmu.edu). Slif originally focuse...