In this blog, let us discuss what is Convolutional Neural Network (CNN) and the architecture behind Convolutional Neural Networks – which are designed to address image recognition systems and classification problems. Convolutional Neural Networks have wide applications in image and video recognition, recommendation systems and natural language processing. Consider this image of the New York skyline, upon first glance you will see a lot of buildings and colors. So how does the computer process this image? The image is broken down into 3 color-channels which is Red, Green and Blue.

The contribution of this paper is two-fold. First, we present ProbCast - a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework to train our model with adversarial training. Second, we propose a framework that lets us transform a deterministic model into a probabilistic one with improved performance. The motivation of the framework is to either transform existing highly accurate point forecast models to their probabilistic counterparts or to train GANs stably by selecting the architecture of GAN's component carefully and efficiently. We conduct experiments over two publicly available datasets namely electricity consumption dataset and exchange-rate dataset. The results of the experiments demonstrate the remarkable performance of our model as well as the successful application of our proposed framework.

We present a causal view on the robustness of neural networks against input manipulations, which applies not only to traditional classification tasks but also to general measurement data. Based on this view, we design a deep causal manipulation augmented model (deep CAMA) which explicitly models possible manipulations on certain causes leading to changes in the observed effect. We further develop data augmentation and test-time fine-tuning methods to improve deep CAMA's robustness. When compared with discriminative deep neural networks, our proposed model shows superior robustness against unseen manipulations. As a by-product, our model achieves disentangled representation which separates the representation of manipulations from those of other latent causes.

We present a generic and flexible Reinforcement Learning (RL) based meta-learning framework for the problem of few-shot learning. During training, it learns the best optimization algorithm to produce a learner (ranker/classifier, etc) by exploiting stable patterns in loss surfaces. Our method implicitly estimates the gradients of a scaled loss function while retaining the general properties intact for parameter updates. Besides providing improved performance on few-shot tasks, our framework could be easily extended to do network architecture search. We further propose a novel dual encoder, affinity-score based decoder topology that achieves additional improvements to performance. Experiments on an internal dataset, MQ2007, and AwA2 show our approach outperforms existing alternative approaches by 21%, 8%, and 4% respectively on accuracy and NDCG metrics. On Mini-ImageNet dataset our approach achieves comparable results with Prototypical Networks. Empirical evaluations demonstrate that our approach provides a unified and effective framework.

Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more heavy computation power and failing to be deployed on edge devices. Besides, the performance boost is highly dependent on redundant labeled data. To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another. KD is often characterized by the so-called `Student-Teacher' (S-T) learning framework and has been broadly applied in model compression and knowledge transfer. This paper is about KD and S-T learning, which are being actively studied in recent years. First, we aim to provide explanations of what KD is and how/why it works. Then, we provide a comprehensive survey on the recent progress of KD methods together with S-T frameworks typically for vision tasks. In general, we consider some fundamental questions that have been driving this research area and thoroughly generalize the research progress and technical details. Additionally, we systematically analyze the research status of KD in vision applications. Finally, we discuss the potentials and open challenges of existing methods and prospect the future directions of KD and S-T learning.

It is a known fact that deep learning models get better with diversity in the data they are fed with. For instance, data in a use case related to healthcare data will be taken from several providers such as patient data, history, workflows of professionals, insurance providers, etc. to ensure such data diversity. These data points that are collected through various interactions of people are fed into a machine learning model, which sits remotely in a data haven spewing predictions without exhausting. However, consider a scenario where one of the providers ceases to offer data to the healthcare project and later requests to delete the provided information. In such a case, does the model remember or forget its learnings from this data?

The Elyra AI Toolkit extends the industry standard JupyterLab user interface with the goal of simplifying development of AI and other data science models. IBM said this week the initial release includes a visual editor for building AI pipelines along with the ability to run interactive notebooks as batch jobs. Other features include Python script execution and a "hybrid runtime" capability based on Jupyter Notebooks' enterprise gateway. The gateway is designed to ease the scaling of enterprise workloads. IBM said Elyra (pronounced, el-EYE-rah) would ease workload development.

Document or text classification is one of the predominant tasks in Natural language processing. It has many applications including news type classification, spam filtering, toxic comment identification, etc. In big organizations the datasets are large and training deep learning text classification models from scratch is a feasible solution but for the majority of real-life problems your dataset is small and if you want to build your machine learning model you need to be smart. In this article (originally posted by Shahul Es on the neptune.ai/blog), I will talk about pragmatic approaches towards text representation which make document classification on small datasets doable.

A team of South Korean researchers created a type of artificial intelligence known as a generative adversarial network using an existing model called pix2pix, they said Feb. 10 in the Journal of Digital Imaging. And when applied to 18F-FDG PET/CT and MRI scan data from hundreds of patients, it accurately segmented and assessed the volume of white matter in the brain.

Machine Learning, Artificial Intelligence, and now Deep Learning have become so overused that they may as well be synonymous with pixie dust and magical incantations. But, approaches utilizing these techniques are quietly altering how organizations face their most pressing challenge in understanding and protecting data. That challenge can be succinctly described as how do you best achieve data knowledge in order to better steward and safeguard information. Knowing your data is essential to protecting your data because you can't protect what you don't understand. Data knowledge is also critical for getting insight, risk profiling, and value from your data.