BC BUSINESS
Saved by @Mollyycolllinss

Time for #PapersThatMakeYouGoHmmm! A weekly summary of new ML papers from arXiv that make me think one or more of:

1. That looks useful!
2. That's an interesting approach!
3. A business could be built around this!
4. How did they do that?!

 Argument Schemes and Dialogue for Explainable Planning

https://t.co/iI3fxAuOcF
Neural Fitted Q Iteration based Optimal Bidding Strategy in Real Time Reactive Power Market_1

https://t.co/rs7fJc8Sws
A design of human-like robust AI machines in object identification

https://t.co/m1Tfm1KYUl
Single Shot Multitask Pedestrian Detection and Behavior Prediction

https://t.co/S3tiOnHoRw
Controlling Synthetic Characters in Simulations: A Case for Cognitive Architectures and Sigma

https://t.co/mjqovCGUhj
Data Poisoning Attacks to Deep Learning Based Recommender Systems

https://t.co/FVr7Z9YiX1
Self-Attention Based Context-Aware 3D Object Detection

https://t.co/UcyP6IUr1V
L2PF -- Learning to Prune Faster

https://t.co/E1ipKSBFk3
DeepPoison: Feature Transfer Based Stealthy Poisoning Attack

https://t.co/B3beuwHBVD
Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead

https://t.co/E9B8E4YZj6
Explainable AI and Adoption of Algorithmic Advisors: an Experimental Study

https://t.co/5Q98CpM89U
Multimodal Gait Recognition for Neurodegenerative Diseases

https://t.co/NkcrwgWfsT
On the Management of Type 1 Diabetes Mellitus with IoT Devices and ML Techniques

https://t.co/EGaHwpI6gC
Compound Word Transformer: Learning to Compose Full-Song Music over Dynamic Directed Hypergraphs

https://t.co/esweLNEoMb
A Comprehensive Study on Optimization Strategies for Gradient Descent In Deep Learning

https://t.co/DnyxRqxNRY
Exploring Text-transformers in AAAI 2021 Shared Task: COVID-19 Fake News Detection in English

https://t.co/NKpQ0gntHy
Low-cost and high-performance data augmentation for deep-learning-based skin lesion classification

https://t.co/NMcnVpRZt5
StarNet: Gradient-free Training of Deep Generative Models using Determined System of Linear Equations

https://t.co/23HkZdcPKe
Adaptive Synthetic Characters for Military Training

https://t.co/5xNFThJlWK
The case for psychometric artificial general intelligence

https://t.co/w1ZJNCAj39
Artificial Intelligence Methods in In-Cabin Use Cases: A Survey

https://t.co/6kFoUSuLpJ
TextBox: A Unified, Modularized, and Extensible Framework for Text Generation

https://t.co/u62zif51D8
Off-Policy Meta-Reinforcement Learning Based on Feature Embedding Spaces

https://t.co/ugJvlG7b3t
Deep Reinforcement Learning with Quantum-inspired Experience Replay

https://t.co/9TBKAAGMmO
Socially Responsible AI Algorithms: Issues, Purposes, and Challenges

https://t.co/58rbKCY9Ru
Internet of Everything enabled solution for COVID-19, its new variants and future pandemics: Framework, Challenges, and Research Directions

https://t.co/OgZKw3Cov6
Deep Neural Network Based Relation Extraction: An Overview

https://t.co/ISBG8c7UzQ
AutoDropout: Learning Dropout Patterns to Regularize Deep Networks

https://t.co/MuUG6LsPUF
Theory-based Habit Modeling for Enhancing Behavior Prediction

https://t.co/UZDtp2A83a
Explainable AI for Robot Failures: Generating Explanations that Improve User Assistance in Fault Recovery

https://t.co/Fcn2uVEsIp
On the Control of Attentional Processes in Vision

https://t.co/B35B7Dk54K
Stochastic Optimization for Vaccine and Testing Kit Allocation for the COVID-19 Pandemic

https://t.co/CF6glQV2nW
Analyzing movies to predict their commercial viability for producers

https://t.co/VaEcSaIJtj
A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning

https://t.co/nKBRaA6the
"Brilliant AI Doctor" in Rural China: Tensions and Challenges in AI-Powered CDSS Deployment

https://t.co/Cix2rinBob
Support Vector Machine and YOLO for a Mobile Food Grading System

https://t.co/VmiOwRZ2gV
To do or not to do: cost-sensitive causal decision-making

https://t.co/9iDr9CogRJ
Political Depolarization of News Articles Using Attribute-aware Word Embeddings

https://t.co/EsOFDI97Q5
Understanding the Ability of Deep Neural Networks to Count Connected Components in Images

https://t.co/gUPQWJ6YEM
Development of a Respiratory Sound Labeling Software for Training a Deep Learning-Based Respiratory Sound Analysis Model

https://t.co/VLdratnPjD
Learn by Guessing: Multi-Step Pseudo-Label Refinement for Person Re-Identification

https://t.co/gTK15Nmoko
Strategic Features for General Games

https://t.co/4Yt3ZTKb8N
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering

https://t.co/44WSpjKDZd
Enhanced Pub/Sub Communications for Massive IoT Traffic with SARSA Reinforcement Learning

https://t.co/UWIa18td2P
Sentiment Analysis for Open Domain Conversational Agent

https://t.co/2EJqPRIvop
If You're Happy, Then You Know It: The Logic of Happiness... and Sadness

https://t.co/PJTcraD0K7
An Ontology Design Pattern for representing Recurrent Situations

https://t.co/7BWFJqKhBJ
DVD: A Diagnostic Dataset for Multi-step Reasoning in Video Grounded Dialogue

https://t.co/tTZKVlvrWe
Transformers in Vision: A Survey

https://t.co/liP1MJY72v
High-resolution land cover change from low-resolution labels: Simple baselines for the 2021 IEEE GRSS Data Fusion Contest

https://t.co/G5sWF4GYiY
Dynamic Knowledge Graphs as Semantic Memory Model for Industrial Robots

https://t.co/PcfTq36heO
Understanding Health Misinformation Transmission: An Interpretable Deep Learning Approach to Manage Infodemics

https://t.co/nwLiRdGkBQ
Anomaly Recognition from surveillance videos using 3D Convolutional Neural Networks

https://t.co/LU634yUAyU
Personal Privacy Protection via Irrelevant Faces Tracking and Pixelation in Video Live Streaming

https://t.co/dL4GJw3y95
Zombie Account Detection Based on Community Detection and Uneven Assignation PageRank

https://t.co/VGkZKfM4ih
How to Train Your Agent to Read and Write

https://t.co/NJJreymjby
Identifying centres of interest in paintings using alignment and edge detection: Case studies on works by Luc Tuymans

https://t.co/sahwzV0akw
Transformer-based Conditional Variational Autoencoder for Controllable Story Generation

https://t.co/mQydI1yWtY
Outline to Story: Fine-grained Controllable Story Generation from Cascaded Events

https://t.co/GARbpQmbFA
Fusion of Federated Learning and Industrial Internet of Things: A Survey

https://t.co/ZoZD7WWSWa
A Framework for Fast Scalable BNN Inference using Googlenet and Transfer Learning

https://t.co/YC83Pv82kf
Neural Networks for Keyword Spotting on IoT Devices

https://t.co/aPwYWpM7vS
AttnMove: History Enhanced Trajectory Recovery via Attentional Network

https://t.co/qjt6g20nX9
Privacy-sensitive Objects Pixelation for Live Video Streaming

https://t.co/GwHIjWYXqJ
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier

https://t.co/ePVpLxTtsX
End-to-End Training of Neural Retrievers for Open-Domain Question Answering

https://t.co/2m9PzQnl65
A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition

https://t.co/cvKIwFmsWQ
RiddleSense: Answering Riddle Questions as Commonsense Reasoning

https://t.co/VPnK6TmMBY
Identity-aware Facial Expression Recognition in Compressed Video

https://t.co/9mNnzvWugT
Iranis: A Large-scale Dataset of Farsi License Plate Characters

https://t.co/taFXmeM6om
Reader-Guided Passage Reranking for Open-Domain Question Answering

https://t.co/2wt7nbg7ap
CIZSL++: Creativity Inspired Generative Zero-Shot Learning

https://t.co/jqsFZI6Bxa
DISCOS: Bridging the Gap between Discourse Knowledge and Commonsense Knowledge

https://t.co/WY8fldH1Un
NeurIPS 2020 EfficientQA Competition: Systems, Analyses and Lessons Learned

https://t.co/eDeIZrFx08
EarlyBERT: Efficient BERT Training via Early-bird Lottery Tickets

https://t.co/3omOhvBIQN
Etat de l'art sur l'application des bandits multi-bras

https://t.co/0zqsbla1ZF
Binary Graph Neural Networks

https://t.co/VZnSpSWJmp
An automated machine learning-genetic algorithm (AutoML-GA) approach for efficient simulation-driven engine design optimization

https://t.co/8pAjZDl9uZ
CoachNet: An Adversarial Sampling Approach for Reinforcement Learning

https://t.co/yibeyARmL3
A Clinical Evaluation of a Low-Cost Strain Gauge Respiration Belt and Machine Learning to Detect Sleep Apnea

https://t.co/7OQTeR0cBz
MRNet: a Multi-scale Residual Network for EEG-based Sleep Staging

https://t.co/KuKpdhWhkD
Robust Text CAPTCHAs Using Adversarial Examples

https://t.co/08spXMzEji
Detecting Log Anomalies with Multi-Head Attention (LAMA)

https://t.co/qXK049ht20
Architectural Patterns for the Design of Federated Learning Systems

https://t.co/MVHtYSIWjm
Coding for Distributed Multi-Agent Reinforcement Learning

https://t.co/t0Re9BrNHd
Demand Forecasting for Platelet Usage: from Univariate Time Series to Multivariate Models

https://t.co/qzrec6IDOG
Handling many conversions per click in modeling delayed feedback

https://t.co/ZrU0uhNPHT
Teach me to play, gamer! Imitative learning in computer games via linguistic description of complex phenomena and decision tree

https://t.co/uXGXX0WLAD
Adversarial Machine Learning for 5G Communications Security

https://t.co/ScIUq3Pklz
From Learning to Relearning: A Framework for Diminishing Bias in Social Robot Navigation

https://t.co/R7k3hDzJ5W
Automatic identification of outliers in Hubble Space Telescope galaxy images

https://t.co/4PafKjJNJl
Learning a binary search with a recurrent neural network. A novel approach to ordinal regression analysis

https://t.co/wthbFhJAlj
RANK: AI-assisted End-to-End Architecture for Detecting Persistent Attacks in Enterprise Networks

https://t.co/Gor8YavtJq
Continuous Glucose Monitoring Prediction

https://t.co/m6ufMRn9vm
Phishing Attacks and Websites Classification Using Machine Learning and Multiple Datasets (A Comparative Analysis)

https://t.co/FFvkJsN5m5
MSED: a multi-modal sleep event detection model for clinical sleep analysis

https://t.co/Ki9FU3eCTC
A spin-glass model for the loss surfaces of generative adversarial networks

https://t.co/k0zRhKrRFh
Active learning for object detection in high-resolution satellite images

https://t.co/ildobu8RWv
RobustSleepNet: Transfer learning for automated sleep staging at scale

https://t.co/SjB1zOJe9N
Homonym Identification using BERT -- Using a Clustering Approach

https://t.co/LcHjpCT4m4
User Response Prediction in Online Advertising

https://t.co/HvZKLMliJw
COVID19-HPSMP: COVID-19 Adopted Hybrid and Parallel Deep Information Fusion Framework for Stock Price Movement Prediction

https://t.co/vqviIbd1Jb
User Ex Machina : Simulation as a Design Probe in Human-in-the-Loop Text Analytics

https://t.co/2V5vFEojhL
An Odor Labeling Convolutional Encoder-Decoder for Odor Sensing in Machine Olfaction

https://t.co/geb8sFURyH
Predicting Illness for a Sustainable Dairy Agriculture: Predicting and Explaining the Onset of Mastitis in Dairy Cows

https://t.co/bEC6qAdAaS
Attention-based Convolutional Autoencoders for 3D-Variational Data Assimilation

https://t.co/XE226wSV7w
Do We Really Need Deep Learning Models for Time Series Forecasting?

https://t.co/s1muXDs5NJ
Statistical learning for accurate and interpretable battery lifetime prediction

https://t.co/gqLMDxZO7D
3D Convolutional Selective Autoencoder For Instability Detection in Combustion Systems

https://t.co/CjjRuGypAO
The data synergy effects of time-series deep learning models in hydrology

https://t.co/BnQMmqfIwc
Node2Seq: Towards Trainable Convolutions in Graph Neural Networks

https://t.co/ChMZRx6IFe
Risk markers by sex and age group for in-hospital mortality in patients with STEMI or NSTEMI: an approach based on machine learning

https://t.co/dz61KNDgri
The Interplay of Demographic Variables and Social Distancing Scores in Deep Prediction of U.S. COVID-19 Cases

https://t.co/tyLUSSQRM4
Model Extraction and Defenses on Generative Adversarial Networks

https://t.co/swz4ZCHmgv
Boarding House Renting Price Prediction Using Deep Neural Network Regression on Mobile Apps

https://t.co/I7U7R7uv4B
COVID-19: Comparative Analysis of Methods for Identifying Articles Related to Therapeutics and Vaccines without Using Labeled Data

https://t.co/yEir3K29sV
Comparing Classification Models on Kepler Data

https://t.co/JZoxxWvywE
Interspeech 2021 Deep Noise Suppression Challenge

https://t.co/xaU6nRRtco
Biosensors and Machine Learning for Enhanced Detection, Stratification, and Classification of Cells: A Review

https://t.co/gJMrXaPGUD
Deep Learning for Fast and Reliable Initial Access in AI-Driven 6G mmWave Networks

https://t.co/kD7xrRcYNu
Mesh Reconstruction from Aerial Images for Outdoor Terrain Mapping Using Joint 2D-3D Learning

https://t.co/HwjjezqQyg
A Review of Artificial Intelligence Technologies for Early Prediction of Alzheimer's Disease

https://t.co/Ak0vrmyogD
An A* Curriculum Approach to Reinforcement Learning for RGBD Indoor Robot Navigation

https://t.co/R4dy1PCIfV
Auto-Encoding Molecular Conformations

https://t.co/21BhsA7GXw
Adversarially trained LSTMs on reduced order models of urban air pollution simulations

https://t.co/u44QNP35Rb
Generating Informative CVE Description From ExploitDB Posts by Extractive Summarization

https://t.co/PByu7o8tul
Data-Driven Copy-Paste Imputation for Energy Time Series

https://t.co/wPbr4eswsu
One vs Previous and Similar Classes Learning -- A Comparative Study

https://t.co/bCxer47W0s
A Priori Generalization Analysis of the Deep Ritz Method for Solving High Dimensional Elliptic Equations

https://t.co/k5xeSGhXxp
Robust R-Peak Detection in Low-Quality Holter ECGs using 1D Convolutional Neural Network

https://t.co/a9uL9mJuCC
Learning the Predictability of the Future

https://t.co/Y7yz6X2MNr
CASS: Towards Building a Social-Support Chatbot for Online Health Community

https://t.co/MjmRThHMyX
WildDeepfake: A Challenging Real-World Dataset for Deepfake Detection

https://t.co/mbpItXkjMf
Recurrent Neural Networks for Stochastic Control Problems with Delay

https://t.co/TEcyk88BDz
A Symmetric Loss Perspective of Reliable Machine Learning

https://t.co/VTARzV3bnx
Fixed-MAML for Few Shot Classification in Multilingual Speech Emotion Recognition

https://t.co/WbqicxzG1V
Integration of Domain Knowledge using Medical Knowledge Graph Deep Learning for Cancer Phenotyping

https://t.co/W61kqz9z7y
Advances in Electron Microscopy with Deep Learning

https://t.co/j3Z1kB4VKQ

More from Business

George Mack
George Mack
@george__mack
THREAD: 15 of the most useful razors and rules I've found.

Rules of thumb that simplify decisions.

Bezos' Razors:

• If unsure what action to take, let your 80-year-old self make it.

• If unsure who to work with, pick the person that has the best chances of breaking you out of a 3rd world prison.

Skinner's Law:

• If procrastinating on an item, you only have 2 options:

1. Make the pain of not doing it greater than the pain of doing it.

2. Make the pleasure of doing it greater than the pleasure of not doing it.

Luck Razor:

• If stuck with 2 equal options, pick the one that feels like it will produce the most luck later down the line.

I used this razor to go for drinks with a stranger rather than watch Netflix.

In hindsight, it was the highest ROI decision I've ever made.

Bragging Razor:

• If someone brags about their success or happiness, assume it’s half what they claim.

• If someone downplays their success or happiness, assume it’s double what they claim.

The map is not the terrain.
ALL , BUSINESS , PRINCIPLES
Zack Hartzman: Hey Listen Games
Zack Hartzman: Hey Lis...
@HeyListenGames_
So I tried to explain the GameStop situation to some of my students using Pokémon. And I think what I said is mostly true so I figured I would share here (A thread)
#GameStop

Let’s say 10 Weedles costs $20. Weedle here is a metaphor for Gamestop’s stock


Ash Ketchum has 10 Weedles.


Gary Oak thinks he’s smart so he’s going to try and short Weedle. He borrows these 10 Weedles from Ash thinking that the price of Weedle will eventually go down. He sells them immediately thinking he can buy them again later at a lower price and return them to Ash then.


After seeing what Gary is planning, Brock and Misty talk to other Pokémon trainers and they all start buying up EVERY Weedle on the market. This will eventually force Gary to buy the Weedles from them. Remember, he needs to eventually return them to Ash since they were borrowed.
BUSINESS
Advertisement
Atharva Kharbade
Atharva Kharbade
@athrvakhrbde
The story of WOW! Momo

"Started from the bottom now we're here"
How WOW! Momo went from borrowing Rs. 30K, to being valued at over Rs. 860 crore


1/

Year 2008, classmates Sagar Daryani and Binod Kumar Homagai had just finished their graduation, and Sagar realized that he was too fragile in math to be able to clear CAT.

2/

But he knew that he's always been passionate about brands. He had Nike, Puma’s stickers/logos in his notebook (that's literally me!)

3/

Sagar and Binod originally got the idea of WOW! Momo after completion of 3rd year of graduation as they were waiting for their results at the age of 21.

They got the idea of WOW! Momo by observing the lady who used to sell tasty momos in front of their college

4/

Sagar and Binod used to research all night together. In the night Binod would make Momo and Sagar Daryani would make toss bread etc.
BUSINESS
Andrew Finn
Andrew Finn
@finnscave
Young, early stage founder asked for any hiring thoughts - figured worth sharing with the twitter-verse if they can be helpful.

1a) Make people do the work they are going to do for you during the interview process.

1b) People talking about work and experience is basically useless, except to evaluate whether this job "makes sense" for someone at this stage of their life - do the dots connect or not? If you can convince people to do a contract project for a month first, even better.

2) Optimize for IQ/horsepower. Talent overruns experience in like 3-6 months and never looks back. If you love someone, but they are missing a skill, you're better off getting them to learn it than hiring someone more skilled but with less upside.

3) Optimize for low drama and ease to work with, in all ways. You want people who just want to get shit done and enjoy themselves, not people who want to bring their personal drama into the workplace.

4) People who went to the best state school in the state they are from, and were overqualified for that school, tend to be undervalued and have a great low ego/high execution/high IQ ratio. They have ivy league brains with middle class values.
BUSINESS
Ezra Klein
Ezra Klein
@ezraklein
So I'd recommend reading this thread from Dave, but I thought about some of these policies, and how they fit into the whole, a lot, and want to offer a different interpretation.


I think California is world leading on progressivism that doesn't ask anyone to give anything up, or accept any major change, right now.

That's what I mean by symbolically progressive, operationally conservative.

Take the 100% renewable energy standard. As @leahstokes has written, these policies often fail in practice. I note our leadership on renewable energy in the piece, but the kind of politics we see on housing and transportation are going foil that if they don't change.

Creating a statewide consumer financial protection agency is great! But again, you're not asking most voters to give anything up or accept any actual changes.

I don't see that as balancing the scales on, say, high-speed rail.

CA is willing to vote for higher taxes, new agencies, etc. It was impressive when LA passed Measure H, a new sales tax to fund homeless shelters. And depressing to watch those same communities pour into the streets to protest shelters being placed near them. That's the rub.
BUSINESS

You May Also Like

Bartosz Ziembinski
Bartosz Ziembinski
@zmbnski
Still wondering about this 🤔


save as q
Q
Jaya_Upadhyaya
Jaya_Upadhyaya
@Jayalko1
SRI VARAHA NARSIMHA, SIMHACHALAM, VIZAG (AP)
#bharatmandir

One of the 32 Narsimha Kshetram of Andhra. It has a unique form of Narsimha, appearing like a shivlingam

It is said that Narsimha’s fierce nature is soothed by worshipping him with Varaha, considered a peaceful deity


The shrine is believed to have been constructed by Prahlada. With time, it crumbled.
In Treta yuga, King Pururava was passing from here in his vimana. The vimana was attracted to this place by a mystic power.
When the place was unearthed, the deity was found.
@GunduHuDuGa


Pururava’s wife, Urvashi, had a dream that the deity should remain covered in sandalwood paste for the whole year except on Akshaya Tritiya.
This practice has continued till date.
The mukhya mandap here, has a pillar kappam stambham believed to possess curative powers.


Chandanotsava/ Chandan Yatra is the most important festival celebrated on Akshaya Tritiya. The sandalwood paste is removed from the moolavar deity and nijarupa darshan (original form of deity) for twelve hours of the day are done by devotees.
ALL
Advertisement
Anu Satheesh \U0001f1ee\U0001f1f3
Anu Satheesh 🇮🇳...
@AnuSatheesh5
Mangottu Bhagavathi Temple
#Palakkad #Kerala
#keralatemples 🚩

Mangottu Bhagavathi Temple is situated in Athipotta near Alathur of palakkad district. Devi is kshipraprasadi here and grants relief to those who worship with full faith.
Mookken Chathen, situated on the Northern 👇


side of the temple, is guarding Devi here.
Story says that, once there lived a weaver named Kuttan who was a Devi Bhaktan. During one festival time Kuttan was so pleased by the Devi Vigraham that he requested her to come along with him. At that time wind blew heavily and Cloths


in Vigraham flew. Kuttan immediately decorated Devi with his cloth which stuck to Vigraham and returned to his village and with his Umbrella. Devi came with him in that Umbrella and stayed in his place. This place is Mangottu Bhagavathi temple now.

Amme Narayana
🙏🕉🙏
ALL
Professor
Professor
@DillikiBiili
So friends here is the thread on the recommended pathway for new entrants in the stock market.

Here I will share what I believe are essentials for anybody who is interested in stock markets and the resources to learn them, its from my experience and by no means exhaustive..

First the very basic : The Dow theory, Everybody must have basic understanding of it and must learn to observe High Highs, Higher Lows, Lower Highs and Lowers lows on charts and their

Even those who are more inclined towards fundamental side can also benefit from Dow theory, as it can hint start & end of Bull/Bear runs thereby indication entry and exits.


Next basic is Wyckoff's Theory. It tells how accumulation and distribution happens with regularity and how the market actually

Dow theory is old but
SCREENERS , ALL , MARKETESSENTIALS
Joey Tawadrous \U0001f1ee\U0001f1ea
Joey Tawadrous 🇮🇪...
@joeytawadrous
1) Core attributes of a promising founder worth following:
- Progress/trajectory over time
- How well they lead a team &
- Make the vision happen
- Most impressed when someone is way ahead of where you thought they would be when you check up/see them a few months later.

2) Indie Makers have such a benefit of being small, fast, nimble workers in comparison to big companies.

We can easily pivot and vastly change a project of ours. We can change as we learn more about our users.

Big companies can take months/years for even the smallest of pivots.

3) Before you find a product market you can pivot your project as many times as necessary until you find something that works.

Then you only have one thing to do: scale, scale, scale.

4) Be obsessed with the little details.
- listen to every single person who uses your product
- reply to every single person who emails you about your product
- ask them what they like and do not like
- iterate your product, make changes, pivot if necessary

5) Paul Graham's (@paulg) name came up with a feeling of great admiration! Naturally! It was Paul who said:

In the early stages of a company just;
- write code
- talk/sell to customers to stress test your idea

Nothing else.
STARTUPS