Deep learning software demands reliability and performance. However, many of the existing deep learning frameworks are software libraries that act as an unsafe DSL in Python and a computation graph interpreter. We present DLVM, a design and implementation of a compiler infrastructure with a linear algebra intermediate representation, algorithmic differentiation by adjoint code generation, domain-specific optimizations and a code generator targeting GPU via LLVM. Designed as a modern compiler infrastructure inspired by LLVM, DLVM is more modular and more generic than existing deep learning compiler frameworks, and supports tensor DSLs with high expressivity. With our prototypical staged DSL embedded in Swift, we argue that the DLVM system enables a form of modular, safe and performant frameworks for deep learning.
Machine Learning (ML) has revamped every domain of life as it provides powerful tools to build complex systems that learn and improve from experience and data. Our key insight is that to solve a machine learning problem, data scientists do not invent a new algorithm each time, but evaluate a range of existing models with different configurations and select the best one. This task is laborious, error-prone, and drains a large chunk of project budget and time. In this paper we present a novel framework inspired by programming by Sketching and Partial Evaluation to minimize human intervention in developing ML solutions. We templatize machine learning algorithms to expose configuration choices as holes to be searched. We share code and computation between different algorithms, and only partially evaluate configuration space of algorithms based on information gained from initial algorithm evaluations. We also employ hierarchical and heuristic based pruning to reduce the search space. Our initial findings indicate that our approach can generate highly accurate ML models. Interviews with data scientists show that they feel our framework can eliminate sources of common errors and significantly reduce development time.
Text in many domains involves a significant amount of named entities. Predict- ing the entity names is often challenging for a language model as they appear less frequent on the training corpus. In this paper, we propose a novel and effective approach to building a discriminative language model which can learn the entity names by leveraging their entity type information. We also introduce two benchmark datasets based on recipes and Java programming codes, on which we evalu- ate the proposed model. Experimental re- sults show that our model achieves 52.2% better perplexity in recipe generation and 22.06% on code generation than the state-of-the-art language models.
Generating structural query language (SQL) queries from natural language is a long-standing open problem. Answering a natural language question about a database table requires modeling complex interactions between the columns of the table and the question. In this paper, we apply the synthesizing approach to solve this problem. Based on the structure of SQL queries, we break down the model to three sub-modules and design specific deep neural networks for each of them. Taking inspiration from the similar machine reading task, we employ the bidirectional attention mechanisms and character-level embedding with convolutional neural networks (CNNs) to improve the result. Experimental evaluations show that our model achieves the state-of-the-art results in WikiSQL dataset.
This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval. We train our network in a supervised way by fully exploiting inter-class diversity and intra-class identity. Classification loss is optimized to maximize inter-class diversity, while intra-pair is introduced to learn representative intra-class identity. We investigate the binary bits distribution related to categories and find out that the effectiveness of binary bits is highly correlated with data categories, and some bits may degrade classification performance of some categories. We then design hash code generation scheme with category mask to filter out bits with negative contribution. Experimental results demonstrate the proposed method outperforms several state-of-the-arts under various evaluation metrics on public datasets.