The field of machine learning arose somewhat independently of the field of statistics. As a result, machine learning experts tend not to emphasize probabilistic thinking. Probabilistic thinking and understanding uncertainty and variation are hallmarks of statistics. By the way, one of the best books about probabilistic thinking is Nate Silver's The Signal and The Noise: Why So Many Predictions Fail But Some Don't. In the medical field, a classic paper is David Spiegelhalter's Probabilistic Prediction in Patient Management and Clinical Trials.

What makes a cartoon caption funny? As one algorithm found: a simple readable sentence, a negation, and a pronoun--but not "he" or "she." The algorithm went on to pick the funniest captions for thousands of the New Yorker's cartoons, and in most cases, it matched the intuition of its editors. Algorithms are getting much better at understanding language, and we are becoming more aware of this through stories like that of IBM Watson winning the Jeopardy quiz. Google released the word2vec tool, and Facebook followed by publishing their speed optimized deep learning modules.

This one is simple, it's when you completely drive yourself. Cars that we mostly drive today belong here, those are the ones that have anti-lock brakes and cruise-control, so they can take over some non-vital processes involved in driving. When the system can take over control in some specific use cases but driver still has to monitor system all the time is here, it's applicable to situations when the car is self-driving the highway and you just sit there and expect it to behave well. This level means that driver doesn't have to monitor the system all the time but has to be in a position where the control can quickly be resumed by a human operator. That means no need to have hands on a steering wheel but you have to jump in at the sounds of the emergency situation, which system can recognize efficiently. When your car drives you to the parking lot you get to the level four, when there is no need for a human operator for a specific use case or a part of a journey.

Yojee Ltd, an Australia-based logistics and supply chain management solution supplier, will partner with Post Media, the parent company of the Phnom Penh Post and Post Khmer, to establish its own technology-based logistics platform on top of Post Media's existing daily newspaper delivery network, the company announced yesterday. A memorandum of understanding (MoU) between the two companies inked yesterday will see Yojee deploy a same-day, next-day delivery logistics service in Cambodia that leverages the efficiency and expertise of Post Media's delivery operations, generating new revenue and synergies. The collaborative partnership will employ Yojee's artificial intelligence (AI) logistics and supply-chain management software to manage delivery of freight and parcels in the Kingdoms' fast-growing e-commerce market. Ed Clarke, managing director of Yojee, said Post Media's nationwide business network and over 1 million active readers will provide a solid foundation for his company's entry into the Cambodian market without any additional asset acquisition costs. "Having this audience to market Yojee's delivery capabilities from day one is a coup for Yojee, as it literally saves us years and significant capital expenditure to acquire such a customer base in any other manner," he said.

A set of molecular descriptors whose length is independent of molecular size is developed for machine learning models that target thermodynamic and electronic properties of molecules. These features are evaluated by monitoring performance of kernel ridge regression models on well-studied data sets of small organic molecules. The features include connectivity counts, which require only the bonding pattern of the molecule, and encoded distances, which summarize distances between both bonded and non-bonded atoms and so require the full molecular geometry. In addition to having constant size, these features summarize information regarding the local environment of atoms and bonds, such that models can take advantage of similarities resulting from the presence of similar chemical fragments across molecules. Combining these two types of features leads to models whose performance is comparable to or better than the current state of the art. The features introduced here have the advantage of leading to models that may be trained on smaller molecules and then used successfully on larger molecules.

Viewing the trajectory of a patient as a dynamical system, a recurrent neural network was developed to learn the course of patient encounters in the Pediatric Intensive Care Unit (PICU) of a major tertiary care center. Data extracted from Electronic Medical Records (EMR) of about 12000 patients who were admitted to the PICU over a period of more than 10 years were leveraged. The RNN model ingests a sequence of measurements which include physiologic observations, laboratory results, administered drugs and interventions, and generates temporally dynamic predictions for in-ICU mortality at user-specified times. The RNN's ICU mortality predictions offer significant improvements over those from two clinically-used scores and static machine learning algorithms.

One of the ubiquitous representation of long DNA sequence is dividing it into shorter k-mer components. Unfortunately, the straightforward vector encoding of k-mer as a one-hot vector is vulnerable to the curse of dimensionality. Worse yet, the distance between any pair of one-hot vectors is equidistant. This is particularly problematic when applying the latest machine learning algorithms to solve problems in biological sequence analysis. In this paper, we propose a novel method to train distributed representations of variable-length k-mers. Our method is based on the popular word embedding model word2vec, which is trained on a shallow two-layer neural network. Our experiments provide evidence that the summing of dna2vec vectors is akin to nucleotides concatenation. We also demonstrate that there is correlation between Needleman-Wunsch similarity score and cosine similarity of dna2vec vectors.

The capacity of a neural network to absorb information is limited by its number of parameters. Conditional computation, where parts of the network are active on a per-example basis, has been proposed in theory as a way of dramatically increasing model capacity without a proportional increase in computation. In practice, however, there are significant algorithmic and performance challenges. In this work, we address these challenges and finally realize the promise of conditional computation, achieving greater than 1000x improvements in model capacity with only minor losses in computational efficiency on modern GPU clusters. We introduce a Sparsely-Gated Mixture-of-Experts layer (MoE), consisting of up to thousands of feed-forward sub-networks. A trainable gating network determines a sparse combination of these experts to use for each example. We apply the MoE to the tasks of language modeling and machine translation, where model capacity is critical for absorbing the vast quantities of knowledge available in the training corpora. We present model architectures in which a MoE with up to 137 billion parameters is applied convolutionally between stacked LSTM layers. On large language modeling and machine translation benchmarks, these models achieve significantly better results than state-of-the-art at lower computational cost.

X-rays are commonly performed imaging tests that use small amounts of radiation to produce pictures of the organs, tissues, and bones of the body. X-rays of the chest are used to detect abnormalities or diseases of the airways, blood vessels, bones, heart, and lungs. In this work we present a stochastic attention-based model that is capable of learning what regions within a chest X-ray scan should be visually explored in order to conclude that the scan contains a specific radiological abnormality. The proposed model is a recurrent neural network (RNN) that learns to sequentially sample the entire X-ray and focus only on informative areas that are likely to contain the relevant information. We report on experiments carried out with more than $100,000$ X-rays containing enlarged hearts or medical devices. The model has been trained using reinforcement learning methods to learn task-specific policies.

Successful human-robot cooperation hinges on each agent's ability to process and exchange information about the shared environment and the task at hand. Human communication is primarily based on symbolic abstractions of object properties, rather than precise quantitative measures. A comprehensive robotic framework thus requires an integrated communication module which is able to establish a link and convert between perceptual and abstract information. The ability to interpret composite symbolic descriptions enables an autonomous agent to a) operate in unstructured and cluttered environments, in tasks which involve unmodeled or never seen before objects; and b) exploit the aggregation of multiple symbolic properties as an instance of ensemble learning, to improve identification performance even when the individual predicates encode generic information or are imprecisely grounded. We propose a discriminative probabilistic model which interprets symbolic descriptions to identify the referent object contextually w.r.t.\ the structure of the environment and other objects. The model is trained using a collected dataset of identifications, and its performance is evaluated by quantitative measures and a live demo developed on the PR2 robot platform, which integrates elements of perception, object extraction, object identification and grasping.