The Machine Learning & Deep Learning Track is where experts in the rapidly expanding fields of Deep Learning and Machine Learning gather to discuss the latest advances, trends, and models in this exciting field. Attend talks, tutorials, and workshops and hear from the creators and top practitioners as they demonstrate and teach the latest models and trends in Machine Learning and Deep Learning to solve problems in business and society.

As the name implies, this course takes a more applied perspective than Andrew Ng's machine learning lecture at Stanford. You will see more code than mathematics. Concepts and algorithms are using the popular Python libraries scikit-learn and Keras.

Over the past few years, there has been an incredible shift towards technology. Major companies have increasingly reoriented themselves around technologies such as artificial intelligence, machine learning and deep learning. While these technologies have garnered a lot of attention in recent years, they have been raved about as the most promising tech reinvigorating innovations across various range of business functions. Machine learning and deep learning typically are forms of AI, but both have unique capabilities in terms of delivering services and benefits to the end-user. Undeniably, while machine learning had a vast history long before deep learning, researchers and service provider companies were making use of ML algorithms to build a variety of models to improve statistics, simplify speech and envisage risk, among other applications.

Researchers from MIT recently collaborated with the University of Brasilia and Yonsei University to estimate the computational limits of deep learning (DL). They stated, "The computational needs of deep learning scale so rapidly that they will quickly become burdensome again." The researchers analysed 1,058 research papers from the arXiv pre-print repository and other benchmark references in order to understand how the performance of deep learning techniques depends on the computational power of several important application areas. They stated, "To understand why DL is so computationally expensive, we analyse its statistical as well as computational scaling in theory. We show DL is not computationally expensive by accident, but by design." They added, "The same flexibility that makes it excellent at modelling the diverse phenomena as well as outperforming the expert models also makes it more computationally expensive in nature.

Limited-angle tomography of strongly scattering quasi-transparent objects is a challenging, highly ill-posed problem with practical implications in medical and biological imaging, manufacturing, automation, and environmental and food security. Regularizing priors are necessary to reduce artifacts by improving the condition of such problems. Recently, it was shown that one effective way to learn the priors for strongly scattering yet highly structured 3D objects, e.g. layered and Manhattan, is by a static neural network [Goy et al, Proc. Natl. Acad. Sci. 116, 19848-19856 (2019)]. Here, we present a radically different approach where the collection of raw images from multiple angles is viewed analogously to a dynamical system driven by the object-dependent forward scattering operator. The sequence index in angle of illumination plays the role of discrete time in the dynamical system analogy. Thus, the imaging problem turns into a problem of nonlinear system identification, which also suggests dynamical learning as better fit to regularize the reconstructions. We devised a recurrent neural network (RNN) architecture with a novel split-convolutional gated recurrent unit (SC-GRU) as the fundamental building block. Through comprehensive comparison of several quantitative metrics, we show that the dynamic method improves upon previous static approaches with fewer artifacts and better overall reconstruction fidelity.

Model-free deep reinforcement learning (RL) has been successful in a range of challenging domains. However, there are some remaining issues, such as stabilizing the optimization of nonlinear function approximators, preventing error propagation due to the Bellman backup in Q-learning, and efficient exploration. To mitigate these issues, we present SUNRISE, a simple unified ensemble method, which is compatible with various off-policy RL algorithms. SUNRISE integrates three key ingredients: (a) bootstrap with random initialization which improves the stability of the learning process by training a diverse ensemble of agents, (b) weighted Bellman backups, which prevent error propagation in Q-learning by reweighing sample transitions based on uncertainty estimates from the ensembles, and (c) an inference method that selects actions using highest upper-confidence bounds for efficient exploration. Our experiments show that SUNRISE significantly improves the performance of existing off-policy RL algorithms, such as Soft Actor-Critic and Rainbow DQN, for both continuous and discrete control tasks on both low-dimensional and high-dimensional environments. Our training code is available at https://github.com/pokaxpoka/sunrise.

This paper describes the system proposed for addressing the research problem posed in Task 10 of SemEval-2020: Emphasis Selection For Written Text in Visual Media. We propose an end-to-end model that takes as input the text and corresponding to each word gives the probability of the word to be emphasized. Our results show that transformer-based models are particularly effective in this task. We achieved the best Matchm score (described in section 2.2) of 0.810 and were ranked third on the leaderboard.

This paper describes our efforts in tackling Task 5 of SemEval-2020. The task involved detecting a class of textual expressions known as counterfactuals and separating them into their constituent elements. Counterfactual statements describe events that have not or could not have occurred and the possible implications of such events. While counterfactual reasoning is natural for humans, understanding these expressions is difficult for artificial agents due to a variety of linguistic subtleties. Our final submitted approaches were an ensemble of various fine-tuned transformer-based and CNN-based models for the first subtask and a transformer model with dependency tree information for the second subtask. We ranked 4-th and 9-th in the overall leaderboard. We also explored various other approaches that involved the use of classical methods, other neural architectures and the incorporation of different linguistic features.

Predicting the potential success of a book in advance is vital in many applications. This could help both publishers and readers in their decision making process whether or not a book is worth publishing and reading, respectively. This prediction could also help authors decide whether a book draft is good enough to send to a publisher. We propose a model that leverages Convolutional Neural Networks along with readability indices. Unlike previous methods, our method includes no count-based, lexical, or syntactic hand-crafted features. Instead, we make use of a pre-trained sentence encoder to encode the book sentences. We highlight the connection between this task and book genre identification by showing that embeddings that are good at capturing the separability of book genres are better for the book success prediction task. We also show that only the first 1K sentences are good enough to predict the successability of books. Our proposed model outperforms strong baselines on this task by as large as 6.4% F1-score.

Background and motivation: Combining Deep Reinforcement Learning (Deep RL) and Health Systems Simulations has significant potential, for both research into improving Deep RL performance and safety, and in operational practice. While individual toolkits exist for Deep RL and Health Systems Simulations, no framework to integrate the two has been established. Aim: Provide a framework for integrating Deep RL Networks with Health System Simulations, and to ensure this framework is compatible with Deep RL agents that have been developed and tested using OpenAI Gym. Methods: We developed our framework based on the OpenAI Gym framework, and demonstrate its use on a simple hospital bed capacity model. We built the Deep RL agents using PyTorch, and the Hospital Simulatation using SimPy. Results: We demonstrate example models using a Double Deep Q Network or a Duelling Double Deep Q Network as the Deep RL agent. Conclusion: SimPy may be used to create Health System Simulations that are compatible with agents developed and tested on OpenAI Gym environments. GitHub repository of code: https://github.com/MichaelAllen1966/learninghospital