View profile

AI Scholar Weekly - Issue #43

AI Scholar Weekly - Issue #43
By Educate AI  • Issue #43 • View online
Comprehensive List of ML Resources; New AI-powered Device that Spots the Early Signs of a Seizure; Winning Solution of Hateful Memes Challenge; New System Shows Robots How to Drive a Car in a Few Steps; Streaming Data in Python with ML; An Information Security Chatbot (and more)

AI Success Stories
Dell Uses AI to Increase Conversions +45%
The multinational leader in technology, Dell, empowers people and communities from across the globe with superior software and hardware. Their marketing team suffered the challenge of declining engagement with their copy which had significant, downstream effects on revenue. Since data is a core part of Dell’s hard drive, their marketing team needed a data-driven solution that supercharges response rates and displays why certain words and phrases outperform others.
Solution: Dell implemented an AI technology that machine-generated marketing copy, to enhance the effectiveness of their email channel and garner data-driven insights for each of their key audiences.
Results:
  • Dell noticed a 50% average increase in CTR
  • 46% average increase in responses from customers. 
  • It also generated a 22% average increase in page visits
  • 77% average increase in add-to-carts
If you have a similar business need or want similar success, Sign up for a 30-minute consultation now and learn how AI can upgrade your business today.
Top AI Research Papers This Week
@EducateAI
@EducateAI
#1 Newly Proposed TinyTL Provides Significant Accuracy Improvements with Little Memory Overhead
Intelligent edge devices have been on the increase in our daily lives. Combining artificial intelligence (AI) and these edge devices, there are many real-world applications such as smart homes, smart retail, autonomous driving, and so on. Tiny Machine Learning (TinyML) technology aims to make computing at the edge cheaper, less expensive, and predictable.
However, state-of-the-art deep learning AI systems typically demand tremendous computational resources and expertise, which hinders the application of edge devices.
There has been a lot of interest and research to this end. Among them is this recently proposed Tiny-Transfer-Learning (TinyTL) for memory-efficient on-device learning that aims to adapt pre-trained models to newly collected data on edge devices.
The critical thing to note about this new method is that unlike conventional methods that focus on reducing the number of parameters or FLOPs, TinyTL directly optimizes the training memory footprint by fixing the memory-heavy modules while learning memory-efficient bias modules.
Researchers also introduce lite residual modules that significantly improve the model’s adaptation capacity with little memory overhead. Extensive experiments on benchmark datasets consistently show the effectiveness and memory-efficiency of TinyTL, paving the way for efficient on-device machine learning.
#2 Google AI: On Device Simultaneous Face, Hand and Pose Prediction
Google recently announced MediaPipe Holistic, a solution that provides a new state-of-the-art human pose topology that unlocks novel use cases. MediaPipe Holistic consists of a new pipeline with an optimized pose, face, and hand components that each run in real-time, with minimum memory transfer between their inference backends, and added support for interchangeability of the three components, depending on the quality/speed tradeoffs.
MediaPipe Holistic estimates the human pose with BlazePose’s pose detector and subsequent keypoint model. Then, using the inferred pose key points, it derives three regions of interest (ROI) crops for each hand (2x) and the face and employs a re-crop model to improve the ROI (details below). The pipeline then crops the full-resolution input frame to these ROIs and applies task-specific face and hand models to estimate their corresponding keypoints. Finally, all key points are merged with those of the pose model to yield the full 540+ keypoints. With its 540+ key points, aims to enable a holistic, simultaneous perception of body language, gesture, and facial expressions. Its blended approach enables remote gesture interfaces, as well as full-body AR, sports analytics, and sign language recognition. 
MediaPipe is available on-device for mobile (Android, iOS) and desktop. However, Google AI is also introducing MediaPipe’s new ready-to-use APIs for research (Python) and web (JavaScript) to ease access to the technology.
The technique for gesture control can unlock various novel use-cases when other human-computer interaction modalities are not convenient. You can try it out in their web demo and prototype your own ideas with it, go here: https://mediapipe.dev/demo/holistic_remote/
#3 A Python OpenFST Wrapper With Support for Custom Semirings and Jupyter Notebooks
In this paper, researchers introduce mFST, a new Python library for working with Finite-State Machines based on OpenFST. mFST is a thin wrapper for OpenFST and exposes all of OpenFST’s methods for manipulating FSTs. 
Additionally, mFST is the only Python wrapper for OpenFST that exposes OpenFST’s ability to define a custom semirings. This makes mFST ideal for developing models that involve learning the weights on a FST or creating neuralized FSTs. mFST has been designed to be easy to get started with and has been previously used in homework assignments for a NLP class as well in projects for integrating FSTs and neural networks. The work exhibits mFST API and how to use mFST to build a simple neuralized FST with PyTorch.
#4 The Winning Solution of Hateful Memes Challenge
Hateful Memes is a new challenge set for multimodal classification, focusing on detecting hate speech in multimodal memes. This paper proposes a new model that combines multimodal with rules, to achieve the first ranking of accuracy and AUROC of 86.8% and 0.923 respectively.
The researcher implemented MRM to VisualBert to enhance model effectiveness in Hateful Memes, and applied several common technologies such as K-fold, model stacking, semi-supervised learning, which significantly improved the AUROC and accuracy of classification. 
The most important thing about the model is the combination of rules extracted from the data set with multimodal framework, which improved both the accuracy and the AUROC by more than 13%. On the other hand, the work shows that the performance of multimodal models on difficult samples is not so good. According to the researcher, the attempts to improve the multimodal framework in the future should focus on it.
#5 Machine Learning for Streaming Data in Python
In machine learning, the conventional approach is to process data in batches or chunks. Batch learning models assume that all the data is available at once. When a new batch of data is available, said models have to be retrained from scratch. The assumption of data availability is a hard constraint for the application of machine learning in multiple real-world applications where data is continuously generated. Additionally, storing historical data requires dedicated storage and processing resources which in some cases might be impractical.
Well, a different approach is to treat data as a stream.
In this paper, researchers introduce River, a machine learning library for dynamic data streams, and continual learning. It provides multiple state-of-the-art learning methods, data generators/transformers, performance metrics, and evaluators for different stream learning problems.
River results from the merger of the two most popular packages for stream learning in Python: Creme and scikit-multi-flow. River introduces a revamped architecture based on the lessons learned from the seminal packages. River’s ambition is to be the go-to library for doing machine learning on streaming data. It is open source under a large community of practitioners and researchers.
Source code available on Github
Read the full paper: ML for Streaming Data in Python
Other Great AI Papers
Alzheimer’s is a disease that affects nearly 50 million people worldwide and there are few ways to detect it before it has had a significant impact. This new Alzheimers detection ML system with an accuracy of 85%, might be able to change this and could help millions! Read more
Research has shown that machine learning (ML) models memorize sensitive information regarding training data which indicates serious privacy risks. This work evaluates ML membership inference risks and shows you why you need to do a systematic and rigorous evaluation of privacy risks for models. Read more
Many chatbots have been proposed to provide different services in many areas such as customer service, sales, and marketing. However, the use of chatbots as advisers in the field of information security is not yet considered. This newly developed chatbot acts as an adviser in information security. Read more
Deep learning has revolutionized speaker recognition, a task of identifying persons from their voices. This work details an exciting progress overview on speaker recognition tasks including speaker verification, identification, diarization, robust speaker recognition, and more, with a focus on deep-learning-based methods. Read more
The increasing demand for radiation therapy to treat cancer has led to a growing focus on improving patient flow in clinics. Knowledge-based planning (KBP) methods promise to reduce treatment lead time by streamlining the treatment planning process. For KBP researchers, the Open Knowledge-Based Planning (OpenKBP) Grand Challenge aims at advancing knowledge-based planning with data and accompanying code-base freely available. Read more
AI/ML Resources
Kaolin is an open-source PyTorch Library for accelerating 3D DL research that makes 3D deep learning applications intuitive and approachable. Specifically, Kaolin provides efficient and easy-to-use tools for constructing 3D deep learning architectures and manipulating 3D data for 3D deep learning researchers and practitioners. Learn more
Want to learn machine learning? Looking for machine learning resources? Here’s a comprehensive list of machine learning resources including open courses, textbooks, tutorials, cheat sheets, and more. You’ve got to check it out!
Top AI News
Seizures are often difficult to detect. This new AI-powered helmet promises to spot the early signs of a seizure and help guide the administration of drugs to help combat the seizures. Read full story
Imagine if robots could learn from watching demonstrations? USC researchers have designed a system that shows robots how to drive a car in just a few steps! Check it out here
MIT researcher’s new system RoboGrammar automates and optimizes robot shapes to help them traverse various terrain types. Robot designers can use it to expand the space of robot structures. Computer-aided creativity in robot design
The UK research and innovation organization has named 15 top researchers for the Turing AI acceleration fellowship. Their research reads like a science fiction novel. From helping doctors pick treatments to improve cybersecurity. Read full story
TensorFlow is now available for the new ARM-based Macs with over 10x speed improvement for common training tasks. Read more
AI Scholar Weekly
Thanks for reading! If this newsletter lights you up, create a ripple effect by sharing it with someone else, and they will also be lit up! And, if you have suggestions, comments, or other thoughts, we would love to hear from you, email me at chris@educateai.org, tweet at  @cdossman, like us on Facebook, or connect with me on LinkedIn and Medium.
Happy Christmas 2020 and Happy Holidays!
Did you enjoy this issue?
Educate AI

AI Scholar Weekly brings you everything new and exciting in the world of Artificial Intelligence, Machine Learning, and Deep Learning every week for free.

In order to unsubscribe, click here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue