With the release of the Titan V, we now entered deep learning hardware limbo. It is unclear if NVIDIA will be able to keep its spot as the main deep learning hardware vendor in 2018 and both AMD and Intel Nervana will have a shot at overtaking NVIDIA. So for consumers, I cannot recommend buying any hardware right now. The most prudent choice is to wait until the hardware limbo passes. This might take as little as 3 months or as long as 9 months.

Breast cancer remains the most common type of cancer and the leading cause of cancer-induced mortality among women with 2.4 million new cases diagnosed and 523,000 deaths per year. Historically, a diagnosis has been initially performed using clinical screening followed by histopathological analysis. Automated classification of cancers using histopathological images is a chciteallenging task of accurate detection of tumor sub-types. This process could be facilitated by machine learning approaches, which may be more reliable and economical compared to conventional methods. To prove this principle, we applied fine-tuned pre-trained deep neural networks.

Named Entity Recognition (NER), or entity extraction is an NLP technique which locates and classifies the named entities present in the text. Named Entity Recognition classifies the named entities into pre-defined categories such as the names of persons, organizations, locations, quantities, monetary values, specialized terms, product terminology and expressions of times. Named Entity Recognition is a part of a broader field called Information Extraction. According to Wikipedia, Information Extraction is the task of automatically extracting structured information from any kind of text, structured and/or unstructured. Natural Language Processing has observed a paradigm shift in accuracy through past few years.

Samsung Electronics is expected to unveil its highly anticipated Galaxy S9 flagship phone next month. Ahead of its launch, the South Korean tech giant has announced its new Exynos 9 Series 9810 processor, which features a powerful custom CPU, very fast gigabit LTE modem and sophisticated deep learning capabilities. Samsung's latest premium application processor is so advanced that it has already been selected as a CES 2018 Innovation Awards Honoree in the Embedded Technologies product category ahead of the big Las Vegas event next week. Built on the 10nm process, the Exynos 9810 is more advanced than its predecessors in more ways than one. The Exynos 9810 is designed to carry out seamless multi-tasking.

The tutorials talk about gradient descent presumably because it is one of the simplest algorithms used for optimization, so it is easy to explain. Since most of such tutorials are rather brief, they focus on simple stuff. There are at least several popular optimization algorithms beyond simple gradient descent that are used for deep learning. Actually people often use different algorithms then gradient descent since they usually converge faster. Some of them have non-constant learning rate (e.g.

The year is coming to an end. I did not write nearly as much as I had planned to. But I'm hoping to change that next year, with more tutorials around Reinforcement Learning, Evolution, and Bayesian Methods coming to WildML! And what better way to start than with a summary of all the amazing things that happened in 2017? Looking back through my Twitter history and the WildML newsletter, the following topics repeatedly came up.

We introduce the first system towards the novel task of answering complex multi-sentence recommendation questions in the tourism domain. Our solution uses a pipeline of two modules: question understanding and answering. For question understanding, we define an SQL-like query language that captures the semantic intent of a question; it supports operators like subset, negation, preference and similarity, which are often found in recommendation questions. We train and compare traditional CRFs as well as bidirectional LSTM-based models for converting a question to its semantic representation. We extend these models to a semi-supervised setting with partially labeled sequences gathered through crowdsourc-ing. We find that our best model performs semi-supervised training of BiDiL-STM CRF with hand-designed features and CCM(Chang et al., 2007) constraints. Finally, in an end to end QA system, our answering component converts our question representation into queries fired on underlying knowledge sources. Our experiments on two different answer corpora demonstrate that our system can significantly outperform baselines with up to 20 pt higher accuracy and 17 pt higher recall.

We propose a modification of the cost function of the Hopfield model whose salient features shine in its Taylor expansion and result in more than pairwise interactions with alternate signs, suggesting a unified framework for handling both with deep learning and network pruning. In our analysis, we heavily rely on the Hamilton-Jacobi correspondence relating the statistical model with a mechanical system. In this picture, our model is nothing but the relativistic extension of the original Hopfield model (whose cost function is a quadratic form in the Mattis magnetization which mimics the non-relativistic Hamiltonian for a free particle). We focus on the low-storage regime and solve the model analytically by taking advantage of the mechanical analogy, thus obtaining a complete characterization of the free energy and the associated self-consistency equations in the thermodynamic limit. On the numerical side, we test the performances of our proposal with MC simulations, showing that the stability of spurious states (limiting the capabilities of the standard Hebbian construction) is sensibly reduced due to presence of unlearning contributions in this extended framework.

Recommender systems play a crucial role in mitigating the problem of information overload by suggesting users' personalized items or services. The vast majority of traditional recommender systems consider the recommendation procedure as a static process and make recommendations following a fixed strategy. In this paper, we propose a novel recommender system with the capability of continuously improving its strategies during the interactions with users. We model the sequential interactions between users and a recommender system as a Markov Decision Process (MDP) and leverage Reinforcement Learning (RL) to automatically learn the optimal strategies via recommending trial-and-error items and receiving reinforcements of these items from users' feedbacks. In particular, we introduce an online user-agent interacting environment simulator, which can pre-train and evaluate model parameters offline before applying the model online. Moreover, we validate the importance of list-wise recommendations during the interactions between users and agent, and develop a novel approach to incorporate them into the proposed framework LIRD for list-wide recommendations. The experimental results based on a real-world e-commerce dataset demonstrate the effectiveness of the proposed framework.

With rapid progress and great successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called \textit{adversarial examples}. Adversarial examples are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying deep neural networks in safety-critical scenarios. Therefore, the attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples against deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications and countermeasures for adversarial examples are investigated. We further elaborate on adversarial examples and explore the challenges and the potential solutions.