Improving Object Classification using Pose Information

We propose a method that exploits pose information in order to improve object classification. A lot of research has focused in other strategies, such as engineering feature extractors, trying different classifiers and even using transfer learning. Here, we use neural network architectures in a multi-task setup, whose outputs predict both the class and the camera azimuth. We investigate both Multi-layer Perceptrons and Convolutional Neural Network architectures, and achieve state-of-the-art results in the challenging NORB dataset.

Deep(ly) Learning the Depth

Xun Victor Suo

We report on the use of deep learning algorithms to perform depth recovery in multiview imaging. We show that if enough training data are provided, a neural network such as multilayer perceptron can be trained to recover the depth in multiview imaging as a regression problem. Such a method can replace camera calibration since no knowledge on the camera configuration is required during training. Another advantage of deep learning for this problem, is the speed of testing; typically a few microseconds per point in the scene. This is a lot better than state-of-art algorithms that require to solve a full optimization problem. In a second part, we have studied a related problem: detecting changes in the camera setting. We have shown that deep learning classifiers can recognize amongst a few (4 or 5) camera settings based only on the projections of points on the cameras, with less than 1% classification error. This is a promising step towards the SLAM problem.

2016

Machine learning approaches to text representation using unlabeled data

Mikaela Keller

With the rapid expansion in the use of computers for producing digitalized textual documents, the need of automatic systems for organizing and retrieving the information contained in large databases has become essential. In general, information retrieval systems rely on a formal description or representation of documents enabling their automatic processing. In the most common representation, the so-called bag-of-words, documents are represented by the words composing them and two documents (or a user query and a document) are considered similar if they have a high number of co-occurring words. In this representation, documents with different, but semantically related terms will be considered as unrelated, and documents using the same terms but in different contexts will be seen as similar. It arises quite naturally that information retrieval systems can use the huge amount of existing textual documents in order to "learn", as humans do, the different uses of words depending on the context. This information can be used to enrich documents' representation. In this thesis dissertation we develop several original machine learning approaches which attempt at fulfilling this aim. As a first approach to document representation we propose a probabilistic model in which documents are assumed to be issued from a mixture of distributions over themes, modeled by a hidden variable conditioning a multinomial distribution over words. Simultaneously, words are assumed to be drawn from a mixture of distributions over topics, modeled by a second hidden variable dependent on the themes. As a second approach, we proposed a neural network which is trained to give a score for the appropriateness of a word in a given context. Finally we present, a multi-task learning approach, which is trained jointly to solve an information retrieval task, while learning on unlabeled data to improve its representation of documents.

EPFL2008

ALPINE: Analog In-Memory Acceleration with Tight Processor Integration for Deep Learning

Giovanni Ansaloni, David Atienza Alonso, Irem Boybat Kara, Joshua Alexander Harrison Klein, Alexandre Sébastien Julien Levisse, Yasir Mahmood Qureshi, Abu Sebastian, Marina Zapater Sancho

Analog in-memory computing (AIMC) cores offers significant performance and energy benefits for neural network inference with respect to digital logic (e.g., CPUs). AIMCs accelerate matrix-vector multiplications, which dominate these applications’ run-time. However, AIMC-centric platforms lack the flexibility of general-purpose systems, as they often have hardcoded data flows and can only support a limited set of processing functions. With the goal of bridging this gap in flexibility, we present a novel system architecture that tightly integrates analog in-memory computing accelerators into multi-core CPUs in general-purpose systems. We developed a powerful gem5-based full system-level simulation framework into the gem5-X simulator, ALPINE, which enables an in-depth characterization of the proposed architecture. ALPINE allows the simulation of the entire computer architecture stack from major hardware components to their interactions with the Linux OS. Within ALPINE, we have defined a custom ISA extension and a software library to facilitate the deployment of inference models. We showcase and analyze a variety of mappings of different neural network types, and demonstrate up to 20.5x/20.8x performance/energy gains with respect to a SIMD-enabled ARM CPU implementation for convolutional neural networks, multi-layer perceptrons, and recurrent neural networks.

2022

Machine learning approaches to text representation using unlabeled data

Mikaela Keller

EPFL2008