• Publications
  • Influence
Fine-grained Analysis of Sentence Embeddings Using Auxiliary Prediction Tasks
TLDR
This work proposes a framework that facilitates better understanding of the encoded representations of sentence vectors and demonstrates the potential contribution of the approach by analyzing different sentence representation mechanisms.
Tradeoffs and Constraints on Neural Representation in Networks of Cortical Neurons
TLDR
This work compared the efficacy of different kinds of “neural codes” to represent both spatial and temporal input features in in vitro networks of rat cortical neurons, indicating the inherent redundancy in neural population activity.
Order-Based Representation in Random Networks of Cortical Neurons
TLDR
This study shows that in spontaneously developing large-scale random networks of cortical neurons in vitro the order in which neurons are recruited following each stimulus is a naturally emerging representation primitive that is invariant to significant temporal changes in spike times.
On the Precarious Path of Reverse Neuro-Engineering
TLDR
It is demonstrated that application of reverse engineering to the study of the design principle of a functional neuro-system with a known mechanism, may result in a perfectly valid but wrong induction of the system's design principle.
Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications
TLDR
This paper presents a novel approach for integrating calls to existing applications into deep learning architectures that was able to train a DNN end-to-end with less data and outperformed a matching DNN that did not interact with the external application.
Analysis of advanced meter infrastructure data of water consumption in apartment buildings
TLDR
The experience of using machine learning techniques over data originating from advanced meter infrastructure (AMI) systems for water consumption in a medium-size city results in significant tangible value to the authorities in terms of increase in technician efficiency and a decrease in the amount of wasted, non-revenue, water.
Neural network gradient-based learning of black-box function interfaces
TLDR
By leveraging the existing precise black-box function during inference, the integrated model generalizes better than a fully differentiable model, and learns more efficiently compared to RL-based methods.
Analysis of sentence embedding models using prediction tasks in natural language processing
TLDR
Results from a previous study on the ability of models to encode basic properties such as content, order, and length are analyzed and led to new insights, such as the effect of word frequency or word distance on the able to encode content and order.
The Verification Cockpit - Creating the Dream Playground for Data Analytics over the Verification Process
TLDR
The Verification Cockpit is described, a holistic centralized data model for the arsenal of verification tools used in modern verification processes, which enables connection of the verification tools and provides rich reporting capabilities as well as hooks to advanced data analytics engines.
Template Aware Coverage - taking coverage analysis to the next level
Understanding the relationship between coverage and test-templates (a generic term we use to describe the inputs for the random stimuli generator) is an important layer in understanding the state and
...
1
2
...