The answer to questions of trust and bias in AI is largely seen in the focus on Explainable AI. Although traditionally viewed as "black boxes", AI and machine learning systems are not ontologically inscrutable.

You may have heard about machine learning from interesting applications like spam filtering, optical character recognition, and computer vision. Getting started with machine learning is long process that involves going through several resources. There are books for newbies, academic papers, guided exercises, and standalone projects. It's easy to lose track of what you need to learn among all these options. So in today's post, I'll list seven steps (and 50 resources) that can help you get started in this exciting field of Computer Science, and ramp up toward becoming a machine learning hero.

Andrew Ng taught one of the most-viewed online courses of all time--more than 1.5 million people have registered to take one of the many sequences of his free online course about machine learning. That experience spurred him to co-found Coursera. Today Ng announced that this summer he's launching sequels to that blockbuster, with a series of courses on the AI concept known as deep learning. For the past two years Ng had been applying concepts of deep learning in the commercial sector, as a chief scientist for the Chinese tech giant Baidu. But he left that company in March, and since then has been working on three undisclosed projects in AI.

During the last few months we have been witnessing a rapid change in the development of artificial intelligence. Nearly on a monthly basis, research that documents how algorithms are over-performing on humans, have been published. With the current pace of advancements in AI one can easily assume that in 10 years from now algorithms will over-perform humans on 80% of today's classified diagnosis. Ten years ago the iPhone got introduced which led to the development of 180.000 registered health apps, which equals 50 apps a day. Yes, a large part of them aren't useful, but we can't ignore the impact apps had on patients and clinicians.

Deep convolutional neural networks (CNNs) can be applied to malware binary detection through images classification. The performance, however, is degraded due to the imbalance of malware families (classes). To mitigate this issue, we propose a simple yet effective weighted softmax loss which can be employed as the final layer of deep CNNs. The original softmax loss is weighted, and the weight value can be determined according to class size. A scaling parameter is also included in computing the weight. Proper selection of this parameter has been studied and an empirical option is given. The weighted loss aims at alleviating the impact of data imbalance in an end-to-end learning fashion. To validate the efficacy, we deploy the proposed weighted loss in a pre-trained deep CNN model and fine-tune it to achieve promising results on malware images classification. Extensive experiments also indicate that the new loss function can fit other typical CNNs with an improved classification performance.

In their classic tutorial paper, Saltzer and Schroeder described the mechanics of protecting information in computer systems, as it was understood in the mid 1970s [1]. They were interested, in particular, in mechanisms for achieving privacy, which they defined as follows: The term "privacy" denotes a socially defined ability of an individual (or organization) to determine whether, when, and to whom personal (or organizational) information is to be released. Saltzer and Schroeder took "security" to refer to the body of techniques for controlling the use or modification of computers or information. In this sense, security is an essential element of guaranteeing privacy. Their definitions are roughly in line with our current ideas, perhaps because they helped shaped those ideas.

Releasing full data records is one of the most challenging problems in data privacy. On the one hand, many of the popular techniques such as data de-identification are problematic because of their dependence on the background knowledge of adversaries. On the other hand, rigorous methods such as the exponential mechanism for differential privacy are often computationally impractical to use for releasing high dimensional data or cannot preserve high utility of original data due to their extensive data perturbation. This paper presents a criterion called plausible deniability that provides a formal privacy guarantee, notably for releasing sensitive datasets: an output record can be released only if a certain amount of input records are indistinguishable, up to a privacy parameter. This notion does not depend on the background knowledge of an adversary. Also, it can efficiently be checked by privacy tests. We present mechanisms to generate synthetic datasets with similar statistical properties to the input data and the same format. We study this technique both theoretically and experimentally. A key theoretical result shows that, with proper randomization, the plausible deniability mechanism generates differentially private synthetic data. We demonstrate the efficiency of this generative technique on a large dataset; it is shown to preserve the utility of original data with respect to various statistical analysis and machine learning measures.

This paper presents VEC-NBT, a variation on the unsupervised graph clustering technique VEC, which improves upon the performance of the original algorithm significantly for sparse graphs. VEC employs a novel application of the state-of-the-art word2vec model to embed a graph in Euclidean space via random walks on the nodes of the graph. In VEC-NBT, we modify the original algorithm to use a non-backtracking random walk instead of the normal backtracking random walk used in VEC. We introduce a modification to a non-backtracking random walk, which we call a begrudgingly-backtracking random walk, and show empirically that using this model of random walks for VEC-NBT requires shorter walks on the graph to obtain results with comparable or greater accuracy than VEC, especially for sparser graphs.

The problem of low rank matrix completion is considered in this paper. To exploit the underlying low-rank structure of the data matrix, we propose a hierarchical Gaussian prior model, where columns of the low-rank matrix are assumed to follow a Gaussian distribution with zero mean and a common precision matrix, and a Wishart distribution is specified as a hyperprior over the precision matrix. We show that such a hierarchical Gaussian prior has the potential to encourage a low-rank solution. Based on the proposed hierarchical prior model, a variational Bayesian method is developed for matrix completion, where the generalized approximate massage passing (GAMP) technique is embedded into the variational Bayesian inference in order to circumvent cumbersome matrix inverse operations. Simulation results show that our proposed method demonstrates superiority over existing state-of-the-art matrix completion methods.

Sales forecast is an essential task in E-commerce and has a crucial impact on making informed business decisions. It can help us to manage the workforce, cash flow and resources such as optimizing the supply chain of manufacturers etc. Sales forecast is a challenging problem in that sales is affected by many factors including promotion activities, price changes, and user preferences etc. Traditional sales forecast techniques mainly rely on historical sales data to predict future sales and their accuracies are limited. Some more recent learning-based methods capture more information in the model to improve the forecast accuracy. However, these methods require case-by-case manual feature engineering for specific commercial scenarios, which is usually a difficult, time-consuming task and requires expert knowledge. To overcome the limitations of existing methods, we propose a novel approach in this paper to learn effective features automatically from the structured data using the Convolutional Neural Network (CNN). When fed with raw log data, our approach can automatically extract effective features from that and then forecast sales using those extracted features. We test our method on a large real-world dataset from CaiNiao.com and the experimental results validate the effectiveness of our method.