Automated prediction of public speaking performance enables novel systems for tutoring public speaking skills. We use the largest open repository---TED Talks---to predict the ratings provided by the online viewers. The dataset contains over 2200 talk transcripts and the associated meta information including over 5.5 million ratings from spontaneous visitors to the website. We carefully removed the bias present in the dataset (e.g., the speakers' reputations, popularity gained by publicity, etc.) by modeling the data generating process using a causal diagram. We use a word sequence based recurrent architecture and a dependency tree based recursive architecture as the neural networks for predicting the TED talk ratings. Our neural network models can predict the ratings with an average F-score of 0.77 which largely outperforms the competitive baseline method.

Nowadays, Machine Learning (ML) is seen as the universal solution to improve the effectiveness of information retrieval (IR) methods. However, while mathematics is a precise and accurate science, it is usually expressed by less accurate and imprecise descriptions, contributing to the relative dearth of machine learning applications for IR in this domain. Generally, mathematical documents communicate their knowledge with an ambiguous, context-dependent, and non-formal language. Given recent advances in ML, it seems canonical to apply ML techniques to represent and retrieve mathematics semantically. In this work, we apply popular text embedding techniques to the arXiv collection of STEM documents and explore how these are unable to properly understand mathematics from that corpus. In addition, we also investigate the missing aspects that would allow mathematics to be learned by computers.

Advanced attack campaigns span across multiple stages and stay stealthy for long time periods. There is a growing trend of attackers using off-the-shelf tools and pre-installed system applications (such as \emph{powershell} and \emph{wmic}) to evade the detection because the same tools are also used by system administrators and security analysts for legitimate purposes for their routine tasks. To start investigations, event logs can be collected from operational systems; however, these logs are generic enough and it often becomes impossible to attribute a potential attack to a specific attack group. Recent approaches in the literature have used anomaly detection techniques, which aim at distinguishing between malicious and normal behavior of computers or network systems. Unfortunately, anomaly detection systems based on point anomalies are too rigid in a sense that they could miss the malicious activity and classify the attack, not an outlier. Therefore, there is a research challenge to make better detection of malicious activities. To address this challenge, in this paper, we leverage Group Anomaly Detection (GAD), which detects anomalous collections of individual data points. Our approach is to build a neural network model utilizing Adversarial Autoencoder (AAE-$\alpha$) in order to detect the activity of an attacker who leverages off-the-shelf tools and system applications. In addition, we also build \textit{Behavior2Vec} and \textit{Command2Vec} sentence embedding deep learning models specific for feature extraction tasks. We conduct extensive experiments to evaluate our models on real-world datasets collected for a period of two months. The empirical results demonstrate that our approach is effective and robust in discovering targeted attacks, pen-tests, and attack campaigns leveraging custom tools.

In this paper, we present work in progress on activity recognition and prediction in real homes using either binary sensor data or depth video data. We present our field trial and set-up for collecting and storing the data, our methods, and our current results. We compare the accuracy of predicting the next binary sensor event using probabilistic methods and Long Short-Term Memory (LSTM) networks, include the time information to improve prediction accuracy, as well as predict both the next sensor event and its mean time of occurrence using one LSTM model. We investigate transfer learning between apartments and show that it is possible to pre-train the model with data from other apartments and achieve good accuracy in a new apartment straight away. In addition, we present preliminary results from activity recognition using low-resolution depth video data from seven apartments, and classify four activities - no movement, standing up, sitting down, and TV interaction - by using a relatively simple processing method where we apply an Infinite Impulse Response (IIR) filter to extract movements from the frames prior to feeding them to a convolutional LSTM network for the classification.

We describe two theorem proving tasks -- premise selection and internal guidance -- for which machine learning has been recently used with some success. We argue that the existing methods however do not correspond to the way how humans approach these tasks. In particular, the existing methods so far lack the notion of a state that is updated each time a choice in the reasoning process is made. To address that, we propose an analogy with tasks such as machine translation, where stateful architectures such as recurrent neural networks have been recently very successful. Then we develop and publish a series of sequence-to-sequence data sets that correspond to the theorem proving tasks using several encodings, and provide the first experimental evaluation of the performance of recurrent neural networks on such tasks.

This article is intended for beginners in deep learning who wish to gain knowledge about probability and statistics and also as a reference for practitioners. In my previous article, I wrote about the concepts of linear algebra for deep learning in a top down approach ( link for the article) (If you do not have enough idea about linear algebra, please read that first).The same top down approach is used here.Providing the description of use cases first and then the concepts. All the example code uses python and numpy.Formulas are provided as images for reuse. Probability is the science of quantifying uncertain things.Most of machine learning and deep learning systems utilize a lot of data to learn about patterns in the data.Whenever data is utilized in a system rather than sole logic, uncertainty grows up and whenever uncertainty grows up, probability becomes relevant. By introducing probability to a deep learning system, we introduce common sense to the system.Otherwise the system would be very brittle and will not be useful.In deep learning, several models like bayesian models, probabilistic graphical models, hidden markov models are used.They depend entirely on probability concepts.

One of the most fascinating advancements in the world of machine learning, is the development of abilities to teach a machine how to understand human communication. This very arm of machine learning is called as Natural Language Processing. This post is an attempt at explaining the basics of Natural Language Processing and how a rapid progress has been made in it with the advancements of deep learning and neural networks. A language, basically is a fixed vocabulary of words which is shared by a community of humans to express and communicate there thoughts. This vocabulary is taught to humans as a part of their growing up process, and mostly remains fixed with few additions each year.

This post is a continuation of my previous post Extreme Rare Event Classification using Autoencoders. In the previous post, we talked about the challenges in an extremely rare event data with less than 1% positively labeled data. We built an Autoencoder Classifier for such processes using the concepts of Anomaly Detection. However, the data we have is a time series. But earlier we used a Dense layer Autoencoder that does not use the temporal features in the data.

Skin cancer is the most common malignancy in fair-skinned populations, and melanoma accounts for the majority of skin cancer–related deaths worldwide [1x[1]Schadendorf, D., van Akkooi, A.C., Berking, C., Griewank, K.G., Gutzmer, R., Hauschild, A. et al. Pattern analysis, not simplified algorithms, is the most reliable method for teaching dermoscopy for melanoma diagnosis to residents in dermatology. The CNN deconstructed digital images of skin lesions and generated its own diagnostic criteria for melanoma detection during training. Several follow-up publications by other authors have demonstrated dermatologist-level skin cancer classification by using deep neural networks (CNN) [4x[4]Marchetti, M.A., Codella, N.C., Dusza, S.W., Gutman, D.A., Helba, B., Kalloo, A. et al. Results of the 2016 international skin imaging collaboration international symposium on biomedical imaging challenge: comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images. A convolutional neural network trained with dermoscopic images performed on par with 145 dermatologists in a clinical melanoma image classification task.

The little Sesame Street muppet has taken the world of Natural Language Processing by storm and the storm is picking up speed. We have seen a number of NLP problems solved by neural network architectures built on top of contextual representations of BERT. To name a few BERT based models have pushed the state of the art for SQUAD 2.0 question answering, GLUE multi task learning, Google natural questions task and Biomedical domain specific tasks -- BioBERT. This opened the door for the amazing developers at Hugging Face who built the PyTorch port for BERT. With this library, geniuses i.e. developers and data scientists can use BERT models for text classification, question answering, fine tuning language model and more.