Complete Machine Learning Package is a comprehensive repository containing 30 notebooks on Python programming, data manipulation, data analysis, data visualization, data cleaning, classical machine learning, Computer Vision and Natural Language Processing(NLP).

It's a classic exercise in high-school art class: a student sits at her desk, charcoal pencil held in one hand, poised over a sheet of paper, while the other hand lies outstretched in front of her, palm up, fingers relaxed so that they curve inward. Then she uses one hand to draw the other. It's a beginner's assignment, but the task of depicting hands convincingly is one of the most notorious challenges in figurative art. I remember it being incredibly frustrating--getting the angles and proportion of each finger right, determining how the thumb connects to the palm, showing one finger overlapping another just so. Too often, I would end up with a bizarrely long pinky, or a thumb jutting out at an impossible angle like a broken bone.

The most recent generation of chatbots has surfaced longstanding concerns about the growing sophistication and accessibility of artificial intelligence. Fears about the integrity of the job market -- from the creative economy to the managerial class -- have spread to the classroom as educators rethink learning in the wake of ChatGPT. Yet while apprehensions about employment and schools dominate headlines, the truth is that the effects of large-scale language models such as ChatGPT will touch virtually every corner of our lives. These new tools raise society-wide concerns about artificial intelligence's role in reinforcing social biases, committing fraud and identity theft, generating fake news, spreading misinformation and more. A team of researchers at the University of Pennsylvania School of Engineering and Applied Science is seeking to empower tech users to mitigate these risks.

I once wrote a simple next word prediction app, similar to the ones found now on your phone when you're texting. You can try it out here: https://kbrenchley.shinyapps.io/PlusOne/. It's basic data science, and it predicts what the next word in your sentence will be. When I wrote it the results could be fairly specific because of the data I trained it on, but now the responses are kind of weak. Just now, texting on my phone and using the first words offered, the text suggestions became "This is the first time I've seen a cat."

This article presents the design, implementation, and evaluation of FLSys, a mobile-cloud federated learning (FL) system, which can be a key component for an open ecosystem of FL models and apps. FLSys is designed to work on smart phones with mobile sensing data. It balances model performance with resource consumption, tolerates communication failures, and achieves scalability. In FLSys, different DL models with different FL aggregation methods can be trained and accessed concurrently by different apps. Furthermore, FLSys provides advanced privacy preserving mechanisms and a common API for third-party app developers to access FL models. FLSys adopts a modular design and is implemented in Android and AWS cloud. We co-designed FLSys with a human activity recognition (HAR) model. HAR sensing data was collected in the wild from 100+ college students during a 4-month period. We implemented HAR-Wild, a CNN model tailored to mobile devices, with a data augmentation mechanism to mitigate the problem of non-Independent and Identically Distributed data. A sentiment analysis model is also used to demonstrate that FLSys effectively supports concurrent models. This article reports our experience and lessons learned from conducting extensive experiments using simulations, Android/Linux emulations, and Android phones that demonstrate FLSys achieves good model utility and practical system performance.

In this paper, to deal with the heterogeneity in federated learning (FL) systems, a knowledge distillation (KD) driven training framework for FL is proposed, where each user can select its neural network model on demand and distill knowledge from a big teacher model using its own private dataset. To overcome the challenge of train the big teacher model in resource limited user devices, the digital twin (DT) is exploit in the way that the teacher model can be trained at DT located in the server with enough computing resources. Then, during model distillation, each user can update the parameters of its model at either the physical entity or the digital agent. The joint problem of model selection and training offloading and resource allocation for users is formulated as a mixed integer programming (MIP) problem. To solve the problem, Q-learning and optimization are jointly used, where Q-learning selects models for users and determines whether to train locally or on the server, and optimization is used to allocate resources for users based on the output of Q-learning. Simulation results show the proposed DT-assisted KD framework and joint optimization method can significantly improve the average accuracy of users while reducing the total delay.

This survey paper is an expanded version of an invited keynote at the ThEdu'22 workshop, August 2022, in Haifa (Israel). After a short introduction on the developments of CAS, DGS and other useful technologies, we show implications in Mathematics Education, and in the broader frame of STEAM Education. In particular, we discuss the transformation of Mathematics Education into exploration-discovery-conjecture-proof scheme, avoiding usage as a black box . This scheme fits well into the so-called 4 C's of 21st Century Education. Communication and Collaboration are emphasized not only between humans, but also between machines, and between man and machine. Specific characteristics of the outputs enhance the need of Critical Thinking. The usage of automated commands for exploration and discovery is discussed, with mention of limitations where they exist. We illustrate the topic with examples from parametric integrals (describing a "cognitive neighborhood" of a mathematical notion), plane geometry, and the study of plane curves (envelopes, isoptic curves). Some of the examples are fully worked out, others are explained and references are given.

We introduce a machine learning-powered course allocation mechanism. Concretely, we extend the state-of-the-art Course Match mechanism with a machine learning-based preference elicitation module. In an iterative, asynchronous manner, this module generates pairwise comparison queries that are tailored to each individual student. Regarding incentives, our machine learning-powered course match (MLCM) mechanism retains the attractive strategyproofness in the large property of Course Match. Regarding welfare, we perform computational experiments using a simulator that was fitted to real-world data. Our results show that, compared to Course Match, MLCM increases average student utility by 4%-9% and minimum student utility by 10%-21%, even with only ten comparison queries. Finally, we highlight the practicability of MLCM and the ease of piloting it for universities currently using Course Match.

Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation methods such as representation interpolation, token replacement, or augmentation with models are applied to tackle this problem. However, these data augmentation methods either potentially cause shifts in decision boundaries (representation interpolation), are not expressive enough (token replacement), or introduce too much computational overhead (augmentation with models). To this end, we propose AugPro (Augmentation with Projection), an effective and efficient data augmentation method for distillation. Our method builds on top of representation interpolation augmentation methods to maintain the diversity of expressions and converts the augmented data to tokens to avoid shifting decision boundaries. It uses simple operations that come with little computational overhead. The results on multiple GLUE tasks show that our methods can improve distillation performance by a large margin at a low time cost. Codes are available at https://github.com/google-research/google-research/tree/master/augpro.

We study online learning problems in which a decision maker wants to maximize their expected reward without violating a finite set of $m$ resource constraints. By casting the learning process over a suitably defined space of strategy mixtures, we recover strong duality on a Lagrangian relaxation of the underlying optimization problem, even for general settings with non-convex reward and resource-consumption functions. Then, we provide the first best-of-many-worlds type framework for this setting, with no-regret guarantees under stochastic, adversarial, and non-stationary inputs. Our framework yields the same regret guarantees of prior work in the stochastic case. On the other hand, when budgets grow at least linearly in the time horizon, it allows us to provide a constant competitive ratio in the adversarial case, which improves over the best known upper bound bound of $O(\log m \log T)$. Moreover, our framework allows the decision maker to handle non-convex reward and cost functions. We provide two game-theoretic applications of our framework to give further evidence of its flexibility. In doing so, we show that it can be employed to implement budget-pacing mechanisms in repeated first-price auctions.