Vincent T. Lee

Energy-efficient hybrid stochastic-binary neural networks for near-sensor computing

Recent advances in neural networks (NNs) exhibit unprecedented success at transforming large, unstructured data streams into compact higher-level semantic information for tasks such as handwriting recognition, image classification, and speech recognition. Ideally, systems would employ near-sensor computation to execute these tasks at sensor endpoints to maximize data reduction and minimize data movement. However, near-sensor computing presents its own set of challenges such as operating power constraints, energy budgets, and communication bandwidth capacities. In this paper, we propose a stochastic-binary hybrid design which splits the computation between the stochastic and binary domains for near-sensor NN applications. In addition, our design uses a new stochastic adder and multiplier that are significantly more accurate than existing adders and multipliers. We also show that retraining the binary portion of the NN computation can compensate for precision losses introduced by shorter stochastic bit-streams, allowing faster run times at minimal accuracy losses. Our evaluation shows that our hybrid stochastic-binary design can achieve 9.8x energy efficiency savings, and application-level accuracies within 0.05% compared to conventional all-binary designs.

A mixed-signal EEG interface circuit for use in first year electronics courses

In their first electronics course, many students find operational amplifiers, analog filters and sensor interface circuitry perplexing and daunting. The purpose of this paper is to present a circuit that addresses these pitfalls. A simplified electroencephelogram (EEG) circuit that is interfaced to a digital backend is proposed. The completed circuit involves using instrumentation amplifiers and filters for the EEG interface. The digital backend helps analyze EEG data on the computer.

NCAM: Near-Data Processing for Nearest Neighbor Search

Emerging classes of computer vision applications demand unprecedented computational resources and operate on large amounts of data. In particular, k-nearest neighbors (kNN), a cornerstone algorithm in these applications, incurs significant data movement. To address this challenge, the underlying architecture and memory subsystems must vertically evolve to address memory bandwidth and compute demands. To enable large-scale computer vision, we propose a new class of associative memories called NCAMs which encapsulate logic with memory to accelerate k-nearest neighbors. We estimate that NCAMs can improve the performance of kNN by orders of magnitude over the best off-the-shelf software libraries (e.g., FLANN) and commodity platforms (e.g., GPUs).

Similarity Search on Automata Processors

Similarity search is a critical primitive for a wide variety of applications including natural language processing, content-based search, machine learning, computer vision, databases, robotics, and recommendation systems. At its core, similarity search is implemented using the k-nearest neighbors (kNN) algorithm, where computation consists of highly parallel distance calculations and a global top-k sort. In contemporary von-Neumann architectures, kNN is bottlenecked by data movement which limits throughput and latency. In this paper, we present and evaluate a novel automata-based algorithm for kNN on the Micron Automata Processor (AP), which is a non-von Neumann near-data processing architecture. By employing near-data processing, the AP minimizes the data movement bottleneck and is able to achieve better performance. Unlike prior work in the automata processing space, our work combines temporal encodings with automata design to augment the space of applications for the AP. We evaluate our designs performance on the AP and compare to state-of-the-art CPU, GPU, and FPGA implementations; we show that the current generation of AP hardware can achieve over 50x speedup over CPUs while maintaining competitive energy efficiency gains. We also propose several automata optimization techniques and simple architectural extensions that highlight the potential of the AP hardware.

POSTER: Application-Driven Near-Data Processing for Similarity Search

Similarity search is a key to important applications such as content-based search, deduplication, natural language processing, computer vision, databases, and graphics. At its core, similarity search manifests as k-nearest neighbors (kNN) which consists of parallel distance calculations and a top-k sort. While kNN is poorly supported by todays architectures, it is ideal for near-data processing because of its high memory bandwidth requirements. This work proposes a near-data processing accelerator for similarity search: the similarity search associative memory (SSAM).