One of the hardest things about building a strong career in Artificial Intelligence, Data Science, or Machine Learning is to develop your skills in Math. Unfortunately, Math is one of those fields that scares a lot of people. Not learning Math properly will seriously compromise your problem-solving skills. For more details- check out my article- Why You need Math for Machine Learning. It focuses on Machine Learning, but the principles apply to many more domains.

Machine learning and specifically deep-learning methods have outperformed human capabilities in many pattern recognition and data processing problems, in game playing, and now also play an increasingly important role in scientific discovery. A key application of machine learning in the molecular sciences is to learn potential energy surfaces or force fields from ab-initio solutions of the electronic Schr\"odinger equation using datasets obtained with density functional theory, coupled cluster, or other quantum chemistry methods. Here we review a recent and complementary approach: using machine learning to aid the direct solution of quantum chemistry problems from first principles. Specifically, we focus on quantum Monte Carlo (QMC) methods that use neural network ansatz functions in order to solve the electronic Schr\"odinger equation, both in first and second quantization, computing ground and excited states, and generalizing over multiple nuclear configurations. Compared to existing quantum chemistry methods, these new deep QMC methods have the potential to generate highly accurate solutions of the Schr\"odinger equation at relatively modest computational cost.

Abstract--We present a method for generating, predicting, and using Spatiotemporal Occupancy Grid Maps (SOGM), which embed future semantic information of real dynamic scenes. We present an auto-labeling process that creates SOGMs from noisy real navigation data. We use a 3D-2D feedforward architecture, trained to predict the future time steps of SOGMs, given 3D lidar frames as input. Our pipeline is entirely self-supervised, thus enabling lifelong learning for real robots. The network is composed of a 3D back-end that extracts rich features and enables the semantic segmentation of the lidar frames, and a 2D front-end that predicts the future information embedded in the SOGM representation, potentially capturing the complexities and uncertainties of real-world multi-agent, multi-future interactions. We also design a navigation system that uses these predicted SOGMs within planning, after they have been transformed into Spatiotemporal Risk Maps (SRMs). We verify our navigation system's abilities in simulation, validate it on a real robot, study SOGM predictions on real data in various circumstances, and Time is represented as a color, from red (now) to yellow (future). REDICTING the future has always fascinated humanity. In this paper, we provide a detailed curiosity for the unknown has never faded. But we tend to description of the collection of algorithms required for these forget that we already predict the future constantly in our daily various tasks, for a complete view of the overall approach, as lives, only it is for a short horizon. Walking in the street, illustrated in Figure 2. catching a falling object, or driving a car, all these actions Some of the algorithms we use have already been introduced require a certain level of anticipation. In the first one [1], we described can become quite good at predicting what might happen for how to automatically annotate 3D lidar points, and train a the next few seconds in many situations; what about robots? In the second one We study this question in the context of a concrete example: [2], our system learned to predict the future of dynamic a robot learning on its own to navigate among humans or scenes as SOGMs. Until now, we only evaluated results in dynamic objects in an indoor space. Our approach allows the a simulated environment.

In this paper, we propose a self-supervised learning solution for human activity recognition with smartphone accelerometer data. We aim to develop a model that learns strong representations from accelerometer signals, in order to perform robust human activity classification, while reducing the model's reliance on class labels. Specifically, we intend to enable cross-dataset transfer learning such that our network pre-trained on a particular dataset can perform effective activity classification on other datasets (successive to a small amount of fine-tuning). To tackle this problem, we design our solution with the intention of learning as much information from the accelerometer signals as possible. As a result, we design two separate pipelines, one that learns the data in time-frequency domain, and the other in time-domain alone. In order to address the issues mentioned above in regards to cross-dataset transfer learning, we use self-supervised contrastive learning to train each of these streams. Next, each stream is fine-tuned for final classification, and eventually the two are fused to provide the final results. We evaluate the performance of the proposed solution on three datasets, namely MotionSense, HAPT, and HHAR, and demonstrate that our solution outperforms prior works in this field. We further evaluate the performance of the method in learning generalized features, by using MobiAct dataset for pre-training and the remaining three datasets for the downstream classification task, and show that the proposed solution achieves better performance in comparison with other self-supervised methods in cross-dataset transfer learning.

Recently, deep neural network (DNN)-based physical layer communication techniques have attracted considerable interest. Although their potential to enhance communication systems and superb performance have been validated by simulation experiments, little attention has been paid to the theoretical analysis. Specifically, most studies in the physical layer have tended to focus on the application of DNN models to wireless communication problems but not to theoretically understand how does a DNN work in a communication system. In this paper, we aim to quantitatively analyze why DNNs can achieve comparable performance in the physical layer comparing with traditional techniques, and also drive their cost in terms of computational complexity. To achieve this goal, we first analyze the encoding performance of a DNN-based transmitter and compare it to a traditional one. And then, we theoretically analyze the performance of DNN-based estimator and compare it with traditional estimators. Third, we investigate and validate how information is flown in a DNN-based communication system under the information theoretic concepts. Our analysis develops a concise way to open the "black box" of DNNs in physical layer communication, which can be applied to support the design of DNN-based intelligent communication techniques and help to provide explainable performance assessment.

Although deep reinforcement learning (RL) has recently enjoyed many successes, its methods are still data inefficient, which makes solving numerous problems prohibitively expensive in terms of data. We aim to remedy this by taking advantage of the rich supervisory signal in unlabeled data for learning state representations. This thesis introduces three different representation learning algorithms that have access to different subsets of the data sources that traditional RL algorithms use: (i) GRICA is inspired by independent component analysis (ICA) and trains a deep neural network to output statistically independent features of the input. GrICA does so by minimizing the mutual information between each feature and the other features. Additionally, GrICA only requires an unsorted collection of environment states. (ii) Latent Representation Prediction (LARP) requires more context: in addition to requiring a state as an input, it also needs the previous state and an action that connects them. This method learns state representations by predicting the representation of the environment's next state given a current state and action. The predictor is used with a graph search algorithm. (iii) RewPred learns a state representation by training a deep neural network to learn a smoothed version of the reward function. The representation is used for preprocessing inputs to deep RL, while the reward predictor is used for reward shaping. This method needs only state-reward pairs from the environment for learning the representation. We discover that every method has their strengths and weaknesses, and conclude from our experiments that including unsupervised representation learning in RL problem-solving pipelines can speed up learning.

This course empowers the students to be more efficient, effective, and productive in modern, real-world ML projects by adopting best practices around reproducible workflows. In particular, it teaches the fundamentals of MLops and how to: a) create a clean, organized, reproducible, end-to-end machine learning pipeline from scratch using MLflow b) clean and validate the data using pytest c) track experiments, code, and results using GitHub and Weights & Biases d) select the best-performing model for production and e) deploy a model using MLflow. Along the way, it also touches on other technologies like Kubernetes, Kubeflow, and Great Expectations and how they relate to the content of the class.

Distribution centers often use robots to move objects as a part of their operations. Objects are carried in bins where each bin can contain multiple objects. In this project, students will have to build a model that can count the number of objects in each bin. A system like this can be used to track inventory and make sure that delivery consignments have the correct number of items. To build this project, students will have to use AWS Sagemaker and good machine learning engineering practices to fetch data from a database, preprocess it and then train a machine learning model.

These are 200 flashcards I made to review everything from my years of ML research, classes, and independent study. Creating them helped me prepare for machine learning engineer interviews and was able to get offers from several companies in 2022 (including Google, Tesla, Samsung, Motional, UiPath, and TikTok). Hopefully other people can benefit from them as well! The PDFs in this repo are mostly for convenience. Questions are loosely based off Chip Huyen's ML Interviews Book questions. However, some slides might be overly technical or academic, and not relevant to engineers.

Deep learning has become essential knowledge for data scientists, researchers, and software developers. The R language APIs for Keras and TensorFlow put deep learning within reach for all R users, even if they have no experience with advanced machine learning or neural networks. This book is a hands-on guide to deep learning using the R language. As you move through it, you'll quickly lock in the foundational ideas of deep learning. The intuitive explanations, crisp illustrations, and clear examples guide you through core DL skills like image processing and text manipulation, and even advanced features like transformers.