The premier global professional body of data science and machine learning professionals -- the Association of Data Scientists (ADaSci), has come out with its much-awaited Deep Learning DevCon 2021 (DLDC). The two-day virtual conference on deep learning will be held on 23rd and 24th September, bringing influential professionals and researchers in the deep learning domain on a single platform. There will be seminars, paper presentations, exhibitions, and hackathons at the summit. A full-day training on deep learning will also be offered, with attendees receiving a certificate of attendance. Moreover, it provides you with the unique opportunity to network with fellow attendees, talk to them, and meet companies virtually.

Have you ever thought about AI ruling over humans, machines giving us commands? My answer to this question is a NO.It will not be possible in the near future. Machines can learn but not understand. They can learn our emotions but still not feel it. We have terms like machine learning, deep learning and not machine understanding or deep understanding right.

Artificial intelligence (AI) has entered its Golden Age. Machine learning requires more data to provide compelling insights on how to optimize human activity. Landsat 9 will fill the gap and feed invaluable information into the most powerful AI recommender, predictive, and classifications systems ever. Artificial intelligence (AI) has entered its Golden Age. Machine learning requires more data to provide compelling insights on how to optimize human activity.

Proteins perform critical processes in all living systems: converting solar energy into chemical energy, replicating DNA, as the basis of highly performant materials, sensing and much more. While an incredible range of functionality has been sampled in nature, it accounts for a tiny fraction of the possible protein universe. If we could tap into this pool of unexplored protein structures, we could search for novel proteins with useful properties that we could apply to tackle the environmental and medical challenges facing humanity. This is the purpose of protein design. Sequence design is an important aspect of protein design, and many successful methods to do this have been developed.

You will find in this course a consice review of the theory with intuitive concepts of the algorithms, and you will be able to put in practice your knowledge with many practical examples using your own datasets.

This work deals with the investigation of bifurcating fluid phenomena using a reduced order modelling setting aided by artificial neural networks. We discuss the POD-NN approach dealing with non-smooth solutions set of nonlinear parametrized PDEs. Thus, we study the Navier-Stokes equations describing: (i) the Coanda effect in a channel, and (ii) the lid driven triangular cavity flow, in a physical/geometrical multi-parametrized setting, considering the effects of the domain's configuration on the position of the bifurcation points. Finally, we propose a reduced manifold-based bifurcation diagram for a non-intrusive recovery of the critical points evolution. Exploiting such detection tool, we are able to efficiently obtain information about the pattern flow behaviour, from symmetry breaking profiles to attaching/spreading vortices, even at high Reynolds numbers.

Nonlinear dynamical systems, either continuous or discrete, may produce chaos, i.e. irregular evolution similar to probabilistic, stochastic motion. Continuous autonomous chaotic systems are described by at least three coupled ordinary nonlinear differential equations that, when solved numerically, result in trajectories with irregular features. In general, non-Hamiltonian cases, the trajectory may fall on a strange attractor that is a chaotic yet distinct structure in the system phase space. Understanding the complex dynamics in phase space is significant especially in the mathematical analysis of the inverse problem. In the latter we are given a time series of discrete data and we want to find whether this set derives from a chaotic dynamical system or it is purely stochastic [1-4].

This paper presents fast non-sampling based methods to assess the risk for trajectories of autonomous vehicles when probabilistic predictions of other agents' futures are generated by deep neural networks (DNNs). The presented methods address a wide range of representations for uncertain predictions including both Gaussian and non-Gaussian mixture models to predict both agent positions and control inputs conditioned on the scene contexts. We show that the problem of risk assessment when Gaussian mixture models (GMMs) of agent positions are learned can be solved rapidly to arbitrary levels of accuracy with existing numerical methods. To address the problem of risk assessment for non-Gaussian mixture models of agent position, we propose finding upper bounds on risk using nonlinear Chebyshev's Inequality and sums-of-squares (SOS) programming; they are both of interest as the former is much faster while the latter can be arbitrarily tight. These approaches only require higher order statistical moments of agent positions to determine upper bounds on risk. To perform risk assessment when models are learned for agent control inputs as opposed to positions, we propagate the moments of uncertain control inputs through the nonlinear motion dynamics to obtain the exact moments of uncertain position over the planning horizon. To this end, we construct deterministic linear dynamical systems that govern the exact time evolution of the moments of uncertain position in the presence of uncertain control inputs. The presented methods are demonstrated on realistic predictions from DNNs trained on the Argoverse and CARLA datasets and are shown to be effective for rapidly assessing the probability of low probability events.

This document sums up our results forthe NLP lecture at ETH in the spring semester 2021. In this work, a BERT based neural network model (Devlin et al.,2018) is applied to the JIGSAW dataset (Jigsaw/Conversation AI, 2019) in order to create a model identifying hateful and toxic comments (strictly seperated from offensive language) in online social platforms (English language), inthis case Twitter. Three other neural network architectures and a GPT-2 (Radfordet al., 2019) model are also applied on the provided data set in order to compare these different models. The trained BERT model is then applied on two different data sets to evaluate its generalisation power, namely on another Twitter data set (Tom Davidson, 2017) (Davidsonet al., 2017) and the data set HASOC 2019 (Thomas Mandl, 2019) (Mandl et al.,2019) which includes Twitter and also Facebook comments; we focus on the English HASOC 2019 data. In addition, it can be shown that by fine-tuning the trained BERT model on these two datasets by applying different transfer learning scenarios via retraining partial or all layers the predictive scores improve compared to simply applying the model pre-trained on the JIGSAW data set. Withour results, we get precisions from 64% to around 90% while still achieving acceptable recall values of at least lower 60s%, proving that BERT is suitable for real usecases in social platforms.

The Human-Machine Interaction (HMI) research field is an important topic in machine learning that has been deeply investigated thanks to the rise of computing power in the last years. The first time, it is possible to use machine learning to classify images and/or videos instead of the traditional computer vision algorithms. The aim of this project is to builda symbiosis between a convolutional neural network (CNN)[1] and a recurrent neural network (RNN) [2] to recognize cultural/anthropological Italian sign language gestures from videos. The CNN extracts important features that later areused by the RNN. With RNNs we are able to store temporal information inside the model to provide contextual information from previous frames to enhance the prediction accuracy. Our novel approach uses different data augmentation techniquesand regularization methods from only RGB frames to avoid overfitting and provide a small generalization error.