Janardhan Rao Doppa

HC-search: a learning framework for search-based structured prediction

Structured prediction is the problem of learning a function that maps structured inputs to structured outputs. Prototypical examples of structured prediction include part-of-speech tagging and semantic segmentation of images. Inspired by the recent successes of search-based structured prediction, we introduce a new framework for structured prediction called HC-Search. Given a structured input, the framework uses a search procedure guided by a learned heuristic H to uncover high quality candidate outputs and then employs a separate learned cost function C to select a final prediction among those outputs. The overall loss of this prediction architecture decomposes into the loss due to H not leading to high quality outputs, and the loss due to C not selecting the best among the generated outputs. Guided by this decomposition, we minimize the overall loss in a greedy stagewise manner by first training H to quickly uncover high quality outputs via imitation learning, and then training C to correctly rank the outputs generated via H according to their true losses. Importantly, this training procedure is sensitive to the particular loss function of interest and the time-bound allowed for predictions. Experiments on several benchmark domains show that our approach significantly outperforms several state-of-the-art methods.

Data-Driven Activity Prediction: Algorithms, Evaluation Methodology, and Applications

We consider a novel problem called Activity Prediction, where the goal is to predict the future activity occurrence times from sensor data. In this paper, we make three main contributions. First, we formulate and solve the activity prediction problem in the framework of imitation learning and reduce it to simple regression learning problem. This approach allows us to leverage powerful regression learners; is easy to implement; and can reason about the relational and temporal structure of the problem with negligible computational overhead. Second, we present several evaluation metrics to evaluate a given activity predictor, and discuss their pros and cons in the context of real-world applications. Third, we evaluate our approach using real sensor data collected from 24 smart home testbeds. We also embed the learned predictor into a mobile device based activity prompter and evaluate the app on multiple participants living in smart homes. Our experimental results indicate that the activity predictor learned with our approach performs better than the baseline methods, and offers a simple and reliable approach to prediction of activities from sensor data.

Prune-and-Score: Learning for Greedy Coreference Resolution

We propose a novel search-based approach for greedy coreference resolution, where the mentions are processed in order and added to previous coreference clusters. Our method is distinguished by the use of two functions to make each coreference decision: a pruning function that prunes bad coreference decisions from further consideration, and a scoring function that then selects the best among the remaining decisions. Our framework reduces learning of these functions to rank learning, which helps leverage powerful off-the-shelf rank-learners. We show that our Prune-and-Score approach is superior to using a single scoring function to make both decisions and outperforms several state-of-the-art approaches on multiple benchmark corpora including OntoNotes.

Learning algorithms for link prediction based on chance constraints

In this paper, we consider the link prediction problem, where we are given a partial snapshot of a network at some time and the goal is to predict the additional links formed at a later time. The accuracy of current prediction methods is quite low due to the extreme class skew and the large number of potential links. Here, we describe learning algorithms based on chance constrained programs and show that they exhibit all the properties needed for a good link predictor, namely, they allow preferential bias to positive or negative class; handle skewness in the data; and scale to large networks. Our experimental results on three real-world domains--co-authorship networks, biological networks and citation networks--show significant performance improvement over baseline algorithms. We conclude by briefly describing some promising future directions based on this work.

Optimizing 3D NoC Design for Energy Efficiency: A Machine Learning Approach

Three-dimensional (3D) Network-on-Chip (NoC) is an emerging technology that has the potential to achieve high performance with low power consumption for multicore chips. However, to fully realize their potential, we need to consider novel 3D NoC architectures. In this paper, inspired by the inherent advantages of small-world (SW) 2D NoCs, we explore the design space of SW network-based 3D NoC architectures. We leverage machine learning to intelligently explore the design space to optimize the placement of both planar and vertical communication links for energy efficiency. We demonstrate that the optimized 3D SW NoC designs perform significantly better than their 3D MESH counterparts. On an average, the 3D SW NoC shows 35% energy-delay-product (EDP) improvement over 3D MESH for the nine PARSEC and SPLASH2 benchmarks considered in this work. The highest performance improvement of 43% was achieved for RADIX. Interestingly, even after reducing the number of vertical links by 50%, the optimized 3D SW NoC performs 25% better than the fully connected 3D MESH, which is a strong indication of the effectiveness of our optimization methodology.

Hybrid network-on-chip architectures for accelerating deep learning kernels on heterogeneous manycore platforms

In recent years, designing specialized manycore heterogeneous architectures for deep learning kernels has become an area of great interest. However, the typical on-chip communication infrastructures employed on conventional manycore platforms are unable to handle both CPU and GPU communication requirements efficiently. Hence, in this paper, our aim is to enhance the performance of heterogeneous manycore architectures through the design of a hybrid NoC consisting of both wireline and wireless links. To this end, we specifically target the resource-intensive backpropagation algorithm commonly used as the training method in deep learning. For backpropagation, the proposed hybrid NoC achieves 1.9× reduction in network latency and improves the network throughput by a factor of 2 with respect to a highly optimized mesh NoC. These network level improvements translate into 25% savings in full system energy-delay-product (EDP). This demonstrates the capability of the proposed hybrid and heterogeneous manycore architecture in accelerating deep learning kernels in an energy-efficient manner.

Design-Space Exploration and Optimization of an Energy-Efficient and Reliable 3-D Small-World Network-on-Chip

A 3-D network-on-chip (NoC) enables the design of high performance and low power many-core chips. Existing 3-D NoCs are inadequate for meeting the ever-increasing performance requirements of many-core processors since they are simple extensions of regular 2-D architectures and they do not fully exploit the advantages provided by 3-D integration. Moreover, the anticipated performance gain of a 3-D NoC-enabled many-core chip may be compromised due to the potential failures of through-silicon-vias that are predominantly used as vertical interconnects in a 3-D IC. To address these problems, we propose a machine-learning-inspired predictive design methodology for energy-efficient and reliable many-core architectures enabled by 3-D integration. We demonstrate that a small-world network-based 3-D NoC (3-D SWNoC) performs significantly better than its 3-D MESH-based counterparts. On average, the 3-D SWNoC shows 35% energy-delay-product improvement over 3-D MESH for the PARSEC and SPLASH2 benchmarks considered in this paper. To improve the reliability of 3-D NoC, we propose a computationally efficient spare-vertical link (sVL) allocation algorithm based on a state-space search formulation. Our results show that the proposed sVL allocation algorithm can significantly improve the reliability as well as the lifetime of 3-D SWNoC.

An Ensemble Architecture for Learning Complex Problem-Solving Techniques from Demonstration

We present a novel ensemble architecture for learning problem-solving techniques from a very small number of expert solutions and demonstrate its effectiveness in a complex real-world domain. The key feature of our “Generalized Integrated Learning Architecture” (GILA) is a set of heterogeneous independent learning and reasoning (ILR) components, coordinated by a central meta-reasoning executive (MRE). The ILRs are weakly coupled in the sense that all coordination during learning and performance happens through the MRE. Each ILR learns independently from a small number of expert demonstrations of a complex task. During performance, each ILR proposes partial solutions to subproblems posed by the MRE, which are then selected from and pieced together by the MRE to produce a complete solution. The heterogeneity of the learner-reasoners allows both learning and problem solving to be more effective because their abilities and biases are complementary and synergistic. We describe the application of this novel learning and problem solving architecture to the domain of airspace management, where multiple requests for the use of airspaces need to be deconflicted, reconciled, and managed automatically. Formal evaluations show that our system performs as well as or better than humans after learning from the same training data. Furthermore, GILA outperforms any individual ILR run in isolation, thus demonstrating the power of the ensemble architecture for learning and problem solving.

ℋC-search for structured prediction in computer vision

The mainstream approach to structured prediction problems in computer vision is to learn an energy function such that the solution minimizes that function. At prediction time, this approach must solve an often-challenging optimization problem. Search-based methods provide an alternative that has the potential to achieve higher performance. These methods learn to control a search procedure that constructs and evaluates candidate solutions. The recently-developed ℋC-Search method has been shown to achieve state-of-the-art results in natural language processing, but mixed success when applied to vision problems. This paper studies whether ℋC-Search can achieve similarly competitive performance on basic vision tasks such as object detection, scene labeling, and monocular depth estimation, where the leading paradigm is energy minimization. To this end, we introduce a search operator suited to the vision domain that improves a candidate solution by probabilistically sampling likely object configurations in the scene from the hierarchical Berkeley segmentation. We complement this search operator by applying the DAgger algorithm to robustly train the search heuristic so it learns from its previous mistakes. Our evaluation shows that these improvements reduce the branching factor and search depth, and thus give a significant performance boost. Our state-of-the-art results on scene labeling and depth estimation suggest that ℋC-Search provides a suitable tool for learning and inference in vision.

Learning to Detect Basal Tubules of Nematocysts in SEM Images

This paper presents a learning approach for detecting nematocysts in Scanning Electron Microscope (SEM) images. The image dataset was collected and made available to us by biologists for the purposes of morphological studies of corals, jellyfish, and other species in the phylum Cnidaria. Challenges for computer vision presented by this biological domain are rarely seen in general images of natural scenes. We formulate nematocyst detection as labeling of a regular grid of image patches. This structured prediction problem is specified within two frameworks: CRF and HC-Search. The CRF uses graph cuts for inference. The HC-Search approach is based on search in the space of outputs. It uses a learned heuristic function (H) to uncover high-quality candidate labelings of image patches, and then uses a learned cost function (C) to select the final prediction among the candidates. While locally optimal CRF inference may be sufficient for images of natural scenes, our results demonstrate that CRF with graph cuts performs poorly on the nematocyst images, and that HC-Search outperforms CRF with graph cuts. This suggests biological images of flexible objects present new challenges requiring further ad- vances of, or alternatives to existing methods.