DeepMind solves a 50-year old problem in Protein Folding Prediction. AlphaFold 2 improves over DeepMind's 2018 AlphaFold system with a new architecture and massively outperforms all competition. In this Video, we take a look at how AlphaFold 1 works and what we can gather about AlphaFold 2 from the little information that's out there. CASP14 Result Bar Chart: https://www.predictioncenter.org/casp14/zscores_final.cgi Paper Title: High Accuracy Protein Structure Prediction Using Deep Learning Abstract: Proteins are essential to life, supporting practically all its functions. They are large complex molecules, made up of chains of amino acids, and what a protein does largely depends on its unique 3D structure.

Deep learning neural network models are fit on training data using the stochastic gradient descent optimization algorithm. Updates to the weights of the model are made, using the backpropagation of error algorithm. The combination of the optimization and weight update algorithm was carefully chosen and is the most efficient approach known to fit neural networks. Nevertheless, it is possible to use alternate optimization algorithms to fit a neural network model to a training dataset. This can be a useful exercise to learn more about how neural networks function and the central nature of optimization in applied machine learning. It may also be required for neural networks with unconventional model architectures and non-differentiable transfer functions.

Data science is nothing if not tedious, in ordinary practice. The initial tedium consists of finding data relevant to the problem you're trying to model, cleaning it, and finding or constructing a good set of features. The next tedium is a matter of attempting to train every possible machine learning and deep learning model to your data, and picking the best few to tune. Then you need to understand the models well enough to explain them; this is especially important when the model will be helping to make life-altering decisions, and when decisions may be reviewed by regulators. Finally, you need to deploy the best model (usually the one with the best accuracy and acceptable prediction time), monitor it in production, and improve (retrain) the model as the data drifts over time.

Here is my attempt to map the research *doctrines* of various groups working on Artificial General Intelligence. Although one might see names of individuals here as well as organizations, take it just as identification of the organization behind the person and a very narrow slice of their overall research portfolio. Note also that several of these parties have not stated that they are working on AGI. One can treat that non-statement as in fact a doctrine. That is, a stance that AGI is too complex and therefore selecting a more pragmatic stance.

There is a renaissance occurring in the field of artificial intelligence. Many are making against the advancements of Deep Learning. Deep Learning is anyway an amazingly radical departure from classical methods. Old style A.I. procedures has zeroed in generally on the legitimate premise of cognition, Deep Learning by contrast works in the territory of cognitive intuition. Deep learning frameworks display behavior that seems biological despite not being founded on biological material.

… artificial intelligence and cognitive innovation applications makes use of deep learning and machine learning algorithms to design more customized …

In the past year, lockdowns and other COVID-19 safety measures have made online shopping more popular than ever, but the skyrocketing demand is leaving many retailers struggling to fulfill orders while ensuring the safety of their warehouse employees. Researchers at the University of California, Berkeley, have created new artificial intelligence software that gives robots the speed and skill to grasp and smoothly move objects, making it feasible for them to soon assist humans in warehouse environments. The technology is described in a paper published online today (Wednesday, Nov. 18) in the journal Science Robotics. Automating warehouse tasks can be challenging because many actions that come naturally to humans -- like deciding where and how to pick up different types of objects and then coordinating the shoulder, arm and wrist movements needed to move each object from one location to another -- are actually quite difficult for robots. Robotic motion also tends to be jerky, which can increase the risk of damaging both the products and the robots.

Real time, accurate passive seismic event detection is a critical safety measure across a range of monitoring applications from reservoir stability to carbon storage to volcanic tremor detection. The most common detection procedure remains the Short-Term-Average to Long-Term-Average (STA/LTA) trigger despite its common pitfalls of requiring a signal-to-noise ratio greater than one and being highly sensitive to the trigger parameters. Whilst numerous alternatives have been proposed, they often are tailored to a specific monitoring setting and therefore cannot be globally applied, or they are too computationally expensive therefore cannot be run real time. This work introduces a deep learning approach to event detection that is an alternative to the STA/LTA trigger. A bi-directional, long-short-term memory, neural network is trained solely on synthetic traces. Evaluated on synthetic and field data, the neural network approach significantly outperforms the STA/LTA trigger both on the number of correctly detected arrivals as well as on reducing the number of falsely detected events. Its real time applicability is proven with 600 traces processed in real time on a single processing unit.

The ability to interpret decisions taken by Machine Learning (ML) models is fundamental to encourage trust and reliability in different practical applications. Recent interpretation strategies focus on human understanding of the underlying decision mechanisms of the complex ML models. However, these strategies are restricted by the subjective biases of humans. To dissociate from such human biases, we propose an interpretation-by-distillation formulation that is defined relative to other ML models. We generalize the distillation technique for quantifying interpretability, using an information-theoretic perspective, removing the role of ground-truth from the definition of interpretability. Our work defines the entropy of supervised classification models, providing bounds on the entropy of Piece-Wise Linear Neural Networks (PWLNs), along with the first theoretical bounds on the interpretability of PWLNs. We evaluate our proposed framework on the MNIST, Fashion-MNIST and Stanford40 datasets and demonstrate the applicability of the proposed theoretical framework in different supervised classification scenarios.

Abstract--In federated learning, models trained on local clients are distilled into a global model. Due to the permutation invariance arises in neural networks, it is necessary to match the hidden neurons first when executing federated learning with neural networks. Through the Bayesian nonparametric framework, Probabilistic Federated Neural Matching (PFNM) matches and fuses local neural networks so as to adapt to varying global model size and the heterogeneity of the data. In this paper, we propose a new method which extends the PFNM with a Kullback-Leibler (KL) divergence over neural components product, in order to make inference exploiting posterior information in both local and global levels. We also show theoretically that The additional part can be seamlessly concatenated into the match-and-fuse progress. Through a series of simulations, it indicates that our new method outperforms popular state-of-the-art federated learning methods in both single communication round and additional communication rounds situation. Considering the inherently private attribute of the data and communication cost, pooling data from many devices at the data center, and conducting centralized training is far from ideal. Thus, federated learning (FL), in which a model is learned from siloed data without centralized together, is proposed to tackle this challenge.