In this paper, we gather 12 workers from a large technology company, as recent participants of a research initiative on the social impact of emerging technologies, to present a collaborative analysis of the opportunities and limitations of dissensus-based approaches to technology research and design. We introduce a series of speculative and deconstructive probes and present findings from their use in four collaborative design sessions. We then draw on the theoretical tradition of Agonism to identify moments of friction, refusal, and disagreement over the course of these sessions. We contend that this approach offers a politically important alternative to consensus-based collaborative design methods and can even surface new rhetorics of contestation within discourses on technology futures. We conclude with a discussion of the importance of worker-authored research and an initial set opportunities, challenges, and paradoxes as a resource for future efforts to "Design for Agonism."

Interactive object understanding, or what we can do to objects and how is a long-standing goal of computer vision. In this paper, we tackle this problem through observation of human hands in in-the-wild egocentric videos. We demonstrate that observation of what human hands interact with and how can provide both the relevant data and the necessary supervision. Attending to hands, readily localizes and stabilizes active objects for learning and reveals places where interactions with objects occur. Analyzing the hands shows what we can do to objects and how. We apply these basic principles on the EPIC-KITCHENS dataset, and successfully learn state-sensitive features, and object affordances (regions of interaction and afforded grasps), purely by observing hands in egocentric videos.

MOTIVATION: An important step in the transcriptomic analysis of individual cells involves manually determining the cellular identities. To ease this labor-intensive annotation of cell-types, there has been a growing interest in automated cell annotation, which can be achieved by training classification algorithms on previously annotated datasets. Existing pipelines employ dataset integration methods to remove potential batch effects between source (annotated) and target (unannotated) datasets. However, the integration and classification steps are usually independent of each other and performed by different tools. We propose JIND (joint integration and discrimination for automated single-cell annotation), a neural-network-based framework for automated cell-type identification that performs integration in a space suitably chosen to facilitate cell classification. To account for batch effects, JIND performs a novel asymmetric alignment in which unseen cells are mapped onto the previously learned latent space, avoiding the need of retraining the classification model for new datasets. JIND also learns cell-type-specific confidence thresholds to identify cells that cannot be reliably classified. RESULTS: We show on several batched datasets that the joint approach to integration and classification of JIND outperforms in accuracy existing pipelines, and a smaller fraction of cells is rejected as unlabeled as a result of the cell-specific confidence thresholds. Moreover, we investigate cells misclassified by JIND and provide evidence suggesting that they could be due to outliers in the annotated datasets or errors in the original approach used for annotation of the target batch. AVAILABILITY AND IMPLEMENTATION: Implementation for JIND is available at https://github.com/mohit1997/JIND and the data underlying this article can be accessed at https://doi.org/10.5281/zenodo.6246322. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

We consider lossless compression based on statistical data modeling followed by prediction-based encoding, where an accurate statistical model for the input data leads to substantial improvements in compression. We propose DZip, a general-purpose compressor for sequential data that exploits the well-known modeling capabilities of neural networks (NNs) for prediction, followed by arithmetic coding. DZip uses a novel hybrid architecture based on adaptive and semi-adaptive training. Unlike most NN-based compressors, DZip does not require additional training data and is not restricted to specific data types. The proposed compressor outperforms general-purpose compressors such as Gzip (29% size reduction on average) and 7zip (12% size reduction on average) on a variety of real datasets, achieves near-optimal compression on synthetic datasets, and performs close to specialized compressors for large sequence lengths, without any human input. While the main limitation of NN-based compressors is generally the encoding/decoding speed, we empirically demonstrate that DZip achieves comparable compression ratio to other NN-based compressors while being several times faster. The source code for DZip and links to the datasets are available at https://github.com/mohit1997/Dzip-torch.

We consider lossless compression based on statistical data modeling followed by prediction-based encoding, where an accurate statistical model for the input data leads to substantial improvements in compression. We propose DZip, a general-purpose compressor for sequential data that exploits the well-known modeling capabilities of neural networks (NNs) for prediction, followed by arithmetic coding. DZip uses a novel hybrid architecture based on adaptive and semi-adaptive training. Unlike most NN based compressors, DZip does not require additional training data and is not restricted to specific data types, only needing the alphabet size of the input data. The proposed compressor outperforms general-purpose compressors such as Gzip (on average 26% reduction) on a variety of real datasets, achieves near-optimal compression on synthetic datasets, and performs close to specialized compressors for large sequence lengths, without any human input. The main limitation of DZip in its current implementation is the encoding/decoding time, which limits its practicality. Nevertheless, the results showcase the potential of developing improved general-purpose compressors based on neural networks and hybrid modeling.

Polynomials, which are widely used to study non-linear systems, have been shown to be extremely useful in analyzing neural networks (NNs). However, the existing methods for training neural networks with polynomial activation functions (PAFs), called as PNNs, are applicable for shallow networks and give a stable performance with quadratic PAFs only. This is due to the optimization issues encountered during training PNNs. We propose a working model for PAFs using a novel normalizing transformation which alleviates the problem of training PNNs with arbitrary degree. Our PAF can be directly used to train shallow PNNs in practice for degrees as high as ten. It can also be utilized to learn multivariate sparse polynomials of small degrees. We also propose a way to train deep CNNs with PAFs which achieve performance similar to deep CNNs with standard activations. Through rigorous experimentation on multiple data sets, we show that PNNs can be effectively trained in practice. This also highlights the potential of the proposed method to support the research on using polynomials to study deep learning.

Sequential data is being generated at an unprecedented pace in various forms, including text and genomic data. This creates the need for efficient compression mechanisms to enable better storage, transmission and processing of such data. To solve this problem, many of the existing compressors attempt to learn models for the data and perform prediction-based compression. Since neural networks are known as universal function approximators with the capability to learn arbitrarily complex mappings, and in practice show excellent performance in prediction tasks, we explore and devise methods to compress sequential data using neural network predictors. We combine recurrent neural network predictors with an arithmetic coder and losslessly compress a variety of synthetic, text and genomic datasets. The proposed compressor outperforms Gzip on the real datasets and achieves near-optimal compression for the synthetic datasets. The results also help understand why and where neural networks are good alternatives for traditional finite context models.

The main issues in processing read-only transactions (ROTs) are correctness, data currency and performance. The popular two-phase locking (2PL) protocol processes the transactions correctly according to serializability criteria, but its performance deteriorates with data contention. To improve the performance, snapshot isolation (SI)-based approaches have been proposed. Even though SI-based approaches improve performance, however they compromise both correctness and data currency aspects. In the literature, an effort has been made to propose improved approaches to process ROTs based on the notion of speculation. The speculation-based approaches improve performance without compromising both correctness and data currency aspects. In this paper, we have extended the speculation-based protocols for processing ROTs in a distributed database systems. It has been identified that an ROT under speculation-based protocols in distributed database systems require a commit phase. In addition, additional messages are required for making speculative versions available to ROTs during the execution phase of an update transaction. In spite of these overheads, the proposed protocols reduce the waiting time of ROTs significantly by increasing the parallelism without violating both correctness and data currency aspects. The simulation experiments show that the proposed protocols significantly improve the performance over 2PL and SI-based protocols.