With recent advancements in deep learning based computer vision models, object detection applications are easier to develop than ever before. Besides significant performance improvements, these techniques have also been leveraging massive image datasets to reduce the need for large datasets. In addition, with current approaches focussing on full end-to-end pipelines, performance has also improved significantly, enabling real-time use cases. Similar to the blogpost I wrote on the different image classification architectures, I will go over two object detection architectures. I will discuss SSD and Faster RCNN, which are currently both available in the Tensorflow Detection API.

With over 20 million downloads and 5 million monthly active users, MyDays was the first-of-its-kind period tracking app on the market. It has seen wide acceptance and is a top-rated app amongst Women's Health, Wellness & Fertility category. However, as time passed, similar period & ovulation tracking apps have mushroomed leading to extensive competition for the app. So, how do you ensure that existing users do not abandon your app for something else? How do you improve engagement levels and offer a more-personalized experience to users?

Learning Deep Learning can be confusing and often very frustrating. In this talk, Sam will set out a roadmap to go from knowing nothing to being fluent in Deep Learning in the fastest way possible. He will highlight courses, frameworks, math, methods, and strategies to get you started and set you on the path to being able to use Deep Learning for real worlds problems and apps. EVENT: FOSSASIA 2018 SPEAKER: Sam Witteveen, Machine Learning Developer Expert Google PERMISSIONS: The original video was published with the Creative Commons Attribution license (reuse allowed).

How are artificial intelligence and data visualization connected? Data is everything to AI, in both creating and teaching it. Intelligent machines, like a humanoid robot that doesn't laugh at dad jokes, are heavily based on data. They are fed specialized algorithms to facilitate deep machine learning. They are also designed to respond while simultaneously processing every new piece of information for predictive analysis.

While Machine Learning (ML) and Deep Learning are part of the AI family, this webinar delves into Deep Learning and its different capabilities. A Deep Learning model is designed to continually analyze data with a logic structure similar to how a human would draw conclusions. To achieve this, Deep Learning uses a layered structure of algorithms called an artificial neural network (ANN). The design of an ANN is inspired by the biological neural network of the human brain. This makes for machine intelligence that's far more capable than that of standard Machine Learning models.

We propose an algorithm to denoise speakers from a single microphone in the presence of non-stationary and dynamic noise. Our approach is inspired by the recent success of neural network models separating speakers from other speakers and singers from instrumental accompaniment. Unlike prior art, we leverage embedding spaces produced with source-contrastive estimation, a technique derived from negative sampling techniques in natural language processing, while simultaneously obtaining a continuous inference mask. Our embedding space directly optimizes for the discrimination of speaker and noise by jointly modeling their characteristics. This space is generalizable in that it is not speaker or noise specific and is capable of denoising speech even if the model has not seen the speaker in the training set. Parameters are trained with dual objectives: one that promotes a selective bandpass filter that eliminates noise at time-frequency positions that exceed signal power, and another that proportionally splits time-frequency content between signal and noise. We compare to state of the art algorithms as well as traditional sparse non-negative matrix factorization solutions. The resulting algorithm avoids severe computational burden by providing a more intuitive and easily optimized approach, while achieving competitive accuracy.

Pancreatic cancer has the poorest prognosis among all cancer types. Intraductal Papillary Mucinous Neoplasms (IPMNs) are radiographically identifiable precursors to pancreatic cancer; hence, early detection and precise risk assessment of IPMN are vital. In this work, we propose a Convolutional Neural Network (CNN) based computer aided diagnosis (CAD) system to perform IPMN diagnosis and risk assessment by utilizing multi-modal MRI. In our proposed approach, we use minimum and maximum intensity projections to ease the annotation variations among different slices and type of MRIs. Then, we present a CNN to obtain deep feature representation corresponding to each MRI modality (T1-weighted and T2-weighted). At the final step, we employ canonical correlation analysis (CCA) to perform a fusion operation at the feature level, leading to discriminative canonical correlation features. Extracted features are used for classification. Our results indicate significant improvements over other potential approaches to solve this important problem. The proposed approach doesn't require explicit sample balancing in cases of imbalance between positive and negative examples. To the best of our knowledge, our study is the first to automatically diagnose IPMN using multi-modal MRI.

Image description task has been invariably examined in a static manner with qualitative presumptions held to be universally applicable, regardless of the scope or target of the description. In practice, however, different viewers may pay attention to different aspects of the image, and yield different descriptions or interpretations under various contexts. Such diversity in perspectives is difficult to derive with conventional image description techniques. In this paper, we propose a customized image narrative generation task, in which the users are interactively engaged in the generation process by providing answers to the questions. We further attempt to learn the user's interest via repeating such interactive stages, and to automatically reflect the interest in descriptions for new images. Experimental results demonstrate that our model can generate a variety of descriptions from single image that cover a wider range of topics than conventional models, while being customizable to the target user of interaction.

This work introduces CLBlast, an open-source BLAS library providing optimized OpenCL routines to accelerate dense linear algebra for a wide variety of devices. It is targeted at machine learning and HPC applications and thus provides a fast matrix-multiplication routine (GEMM) to accelerate the core of many applications (e.g. deep learning, iterative solvers, astrophysics, computational fluid dynamics, quantum chemistry). CLBlast has five main advantages over other OpenCL BLAS libraries: 1) it is optimized for and tested on a large variety of OpenCL devices including less commonly used devices such as embedded and low-power GPUs, 2) it can be explicitly tuned for specific problem-sizes on specific hardware platforms, 3) it can perform operations in half-precision floating-point FP16 saving bandwidth, time and energy, 4) it has an optional CUDA back-end, 5) and it can combine multiple operations in a single batched routine, accelerating smaller problems significantly. This paper describes the library and demonstrates the advantages of CLBlast experimentally for different use-cases on a wide variety of OpenCL hardware.

Backpropagation algorithm is indispensable for the training of feedforward neural networks. It requires propagating error gradients sequentially from the output layer all the way back to the input layer. The backward locking in backpropagation algorithm constrains us from updating network layers in parallel and fully leveraging the computing resources. Recently, several algorithms have been proposed for breaking the backward locking. However, their performances degrade seriously when networks are deep. In this paper, we propose decoupled parallel backpropagation algorithm for deep learning optimization with convergence guarantee. Firstly, we decouple the backpropagation algorithm using delayed gradients, and show that the backward locking is removed when we split the networks into multiple modules. Then, we utilize decoupled parallel backpropagation in two stochastic methods and prove that our method guarantees convergence to critical points for the non-convex problem. Finally, we perform experiments for training deep convolutional neural networks on benchmark datasets. The experimental results not only confirm our theoretical analysis, but also demonstrate that the proposed method can achieve significant speedup without loss of accuracy.