Probing The Full Monty Hall Problem
Probing The Full Monty Hall Problem
A tutorial on the Monty Hall problem in statistics.
6 points
0 issues
Srishti Saha
High Dimension Data Analysis - A tutorial and review for Dimensionality Reduction Techniques
High Dimension Data Analysis - A tutorial and review for Dimensionality Reduction Techniques
This article explains and provides a comparative study of a few techniques for dimensionality reduction. It dives into the mathematical explanation of several feature selection and feature transformation techniques, while also providing the algorithmic representation and implementation of some other techniques. Lastly, it also provides a very brief review of various other works done in this space.
26 points
0 issues
The application of Hamilton-Jacobi equation in reaction-diffusion equations.
The application of Hamilton-Jacobi equation in reaction-diffusion equations.
Hamilton-Jacobi equation
0 points
0 issues
Chandra Chekuri
Probability: The Basics
Probability: The Basics
These notes are intended to provide a quick refresher on basics of probability before introduction to the use of randomization in algorithms.
0 points
0 issues
Group Equivariant Convolutional Networks in Medical Image Analysis
Group Equivariant Convolutional Networks in Medical Image Analysis
This is a brief review of G-CNNs' applications in medical image analysis, including fundamental knowledge of group equivariant convolutional networks, and applications in medical images' classification and segmentation.
8 points
0 issues
Information Theory in Machine Learning
Information Theory in Machine Learning
This review gives a comprehensive study of application of information theory in Machine Learning methods and algorithms.
4 points
0 issues
Pranat
Topological Aspects Of Gauge Theories
Topological Aspects Of Gauge Theories
In this article we shall discuss gauge theories in non-trivial topology configuration spaces.
1 points
0 issues
The Smart Fire Extinguisher - A Sprinkler System Alternative for Early Fire Detection and Prevention
The Smart Fire Extinguisher - A Sprinkler System Alternative for Early Fire Detection and Prevention
This article describes the development of a modular, compact, low cost sprinkler system alternative for early fire detection and prevention. It goes through building a functional system and includes a video summary featuring the finalized prototype.
18 points
0 issues
@jakewhinnery @wilderbuchanan @adarshkumar @braedenswidenbank @danielwinek @atlasyuen
Good Vibes- Characterizing Low Cost Piezoelectric Sensors for Industry
Good Vibes- Characterizing Low Cost Piezoelectric Sensors for Industry
This project characterizes piezoelectric vibration sensors and determines their utility in impact detection applications. The team developed one-dimensional and two-dimensional testing apparatuses in order to predict the height and location of impact of a dropped ball using this inexpensive sensor. After attempting a method of trilateration to limited success, a discrete integration-based approach was developed to predict the location of impact. Through optimized experimentation processes and discretized algorithms, the project was able to predict the impact location within a 10 cm by 10 cm square with a calculated accuracy of 79%.
17 points
0 issues
Invariant Information Clustering
Invariant Information Clustering
This paper introduces a principled clustering objective based on maximizing Mutual Information (MI) between paired data samples under a bottleneck, equivalent to distilling their shared abstract content (co-clustering), that tends to avoid degenerate clustering solutions.
0 points
0 issues
The use of Mathpix OCR with EDICO scientific editor to help blind Students in STEM education
The use of Mathpix OCR with EDICO scientific editor to help blind Students in STEM education
In this tutorial we'll show how Mathpix OCR is helpful to instantly transpose math and science assignments both in braille and speech. We'll use the free EDICO Scientific Editor to demonstrate how a math assignment can be imported using Mathpix technology, and how it can be solved using a Refreshable Braille Display.
3 points
0 issues
L^p^ → L^∞^
L^p^ → L^∞^
A short proof of a thought-provoking relation between the -norms.
1 points
0 issues
Shaoxiong Ji and Teemu Saravirta and Shirui Pan and Guodong Long and Anwar Walid
Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
Emerging Trends in Federated Learning: From Model Fusion to Federated X Learning
Federated learning is a new learning paradigm that decouples data collection and model training via multi-party computation and model aggregation. As a flexible learning setting, federated learning has the potential to integrate with other learning frameworks. We conduct a focused survey of federated learning in conjunction with other learning algorithms.
1 points
0 issues
Event Camera: the Next Generation of Visual Perception System
Event Camera: the Next Generation of Visual Perception System
Event camera can extend computer vision to scenarios where it is currently incompetent. In the following decades, it is hopeful that event cameras will be mature enough to be mass-produced, to have dedicated algorithms, and to show up in widely-used products.
27 points
0 issues
Emil Junker
Manipulative Attacks in Group Identification
Manipulative Attacks in Group Identification
This review provides an introduction to the group identification problem and gives an overview of the feasibility and computational complexity of manipulative attacks in group identification.
2 points
0 issues
Data Augmentation in Automatic Speech Recognition
Data Augmentation in Automatic Speech Recognition
An overview of recent advancements in data augmentation for automatic speech recognition.
0 points
0 issues
Generative Adversarial Networks, their variants and their evaluation
2 points
0 issues
Go-Explore: Reinforcement Learning Algorithms Tackling Hard-Explore Tasks
Go-Explore: Reinforcement Learning Algorithms Tackling Hard-Explore Tasks
A new family of reinforcement learning algorithms, Go-Explore, surpasses all previous approaches on hard-explore Atari games by addressing detachment and derailment.
1 points
0 issues
The bulk of machine learning models have a tendancy to rely too strongly to the distribution of the data on which they have been trained. Through this review paper I propose to discuss about ways to design an image classifier able to generalize well on a different but related distribution from its training one.
3 points
0 issues
Deep Sketch Generation Models
Deep Sketch Generation Models
This article reviews the recent aproaches and datasets in the deep generative sketch modelling field that takes the human-machine creative collaboration one step closer.
2 points
0 issues
Aniket Agarwal ,
Ayush Mangal*
,
Vipul*
Visual Relationship Detection using Scene Graphs - A Survey
Visual Relationship Detection using Scene Graphs - A Survey
This review gives an introduction to Scene Graphs and their usage in various downstream tasks. Many of the recent methods for its generation have been discussed here in detail along with a detailed comparison between them.
3 points
0 issues
Devi Sandeep Endluri
,
Chinmayee Rane
Handwriting Text Recognition
Handwriting Text Recognition
This review introduces Handwriting Text Recognition (HTR), then mentions the different group of approaches for HTR, and finally summarizes the latest research in OCR techniques for offline handwritten recognition on documents.
1 points
0 issues
CHERHYKALO DENYS
Biomorphic AI
Biomorphic AI
In this chapter, we analyze current advances in AI development and their biological implications. I believe that it will be possible not only to convey information more easily, but also to create new ideas of improvement of modern algorithms using AI.
0 points
0 issues
Chandra Chekuri
Approximation Algorithm: Survivable Network Design Problem
Approximation Algorithm: Survivable Network Design Problem
These are lecture notes for a course on approximation algorithms. Chapter 13: Survivable Network Design Problem.
1 points
0 issues
@Yuxuan Wu
,
Feng Shen and Dingjie Xu
In recent years, the environmental perception technology for robotic system has attracted a lot of attention from researchers, but only a little of studies on environmental perception technology are focused on the space underground Meanwhile, in the field of mobile robotic systems, with the development of research on underground emergency hedging and buried targets' high-resolution fault imaging, more and more attention has also been paid to underground environ-mental detection and perception. This article proposes a ground-penetrating radar-based underground environmental perception radar for mobile robotic system indoors.
1 points
0 issues
Electron-Positron Pair Production in Plasma's: Implications for Magneto-sonic Waves
Electron-Positron Pair Production in Plasma's: Implications for Magneto-sonic Waves
I discuss the temperature limit in which pair production becomes important in plasma's. I also discuss the effect of pair production on plasma's modeled in the fluid limit.
0 points
0 issues
@Yuxuan Wu
Reconfigurable Computing Course Associated with the Long Short-Term Memory and the High-Level-Synthesize
Reconfigurable Computing Course Associated with the Long Short-Term Memory and the High-Level-Synthesize
Long short-term memory(LSTM)is a periodic neural network that is suitable for predicting and processing time series intervals and relatively long-delayed important events. In this paper, there are five Lab about the basic principles of LSTM and the methods of generating IP core in the Vivado HLS that has been finished. In addition, the results are confirmed on Zedboard. This experimental course help us understand the principle of LSTM and acquire the skills of cooperative development of ARM and FPGA.
0 points
0 issues
Andrew Ng
Introduction to Factor Analysis
Introduction to Factor Analysis
These notes from Andrew Ng's CS229 course in Machine Learning discuss factor analysis.
1 points
0 issues
Production principle of road and Bridge
Production principle of road and Bridge
This paper introduces some methods and principles in the production process of roads and bridges, and some places that are easy to ignore, for beginners' reference.
2 points
0 issues
@SimonTropp
Targeted Proton Therapy for Safer Treatment of Brain Tumors
Targeted Proton Therapy for Safer Treatment of Brain Tumors
Radiation therapy tends to harm healthy tissue near the treated tumor, thereby increasing the risk of side effects and fatal outcomes in the context of brain tumors. This research paper investigates proton radiation therapy as a viable and generally safer option for the treatment of tumors in sensitive areas like the brain.
5 points
0 issues
Tyler Jones @tyjones1312
The enhanced processing power inherent in a proposed error-corrected quantum computer promises to accelerate the training of deep neural networks, among many other applications. In this review, we outline a major component of current quantum computers which requires improvement before this promise can be fulfilled, and reflect on the ways in which deep learning itself can alleviate this problem.
13 points
0 issues
Chandra Chekuri
Approximation Algorithms: Primal Dual for Constrained Forest Problems
Approximation Algorithms: Primal Dual for Constrained Forest Problems
These are lecture notes for a course on approximation algorithms. Chapter 12: Primal Dual for Constrained Forest Problems.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Steiner Forest Problem
Approximation Algorithms: Steiner Forest Problem
These are lecture notes for a course on approximation algorithms. Chapter 11: Steiner Forest Problem.
0 points
0 issues
Hj Hu
Distribution
Distribution
This paper is concerned with definition of distribution.Some examples about distribution also are given in this paper.
1 points
0 issues
Chandra Chekuri
Approximation Algorithms: Introduction to Network Design
Approximation Algorithms: Introduction to Network Design
These are lecture notes for a course on approximation algorithms. Chapter 10: Introduction to Network Design.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Clustering and Facility Location
Approximation Algorithms: Clustering and Facility Location
These are lecture notes for a course on approximation algorithms. Chapter 9: Clustering and Facility Location.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Introduction to Local Search
Approximation Algorithms: Introduction to Local Search
These are lecture notes for a course on approximation algorithms. Chapter 8: Introduction to Local Search.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Congestion Minimization in Networks
Approximation Algorithms: Congestion Minimization in Networks
These are lecture notes for a course on approximation algorithms. Chapter 7: Congestion Minimization in Networks.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Unrelated Machine Scheduling and Generalized Assignment
Approximation Algorithms: Unrelated Machine Scheduling and Generalized Assignment
These are lecture notes for a course on approximation algorithms. Chapter 6: Unrelated Machine Scheduling and Generalized Assignment.
0 points
0 issues
Introduction to Social Dynamics through Tree Surgery
Introduction to Social Dynamics through Tree Surgery
This is a tutorial for predicting the behavior of large societies using so-called “tree surgery”. It introduces the theoretical and algorithmic methods as an alternative or a complement to agent-based simulations. The tools can be used to predict the emergent behavior of a large society of independent agents in many stylized situations - deciding to wear a facemask outdoors, to use a fork in medieval Italy [1], to rebel against an oppressive government.
5 points
0 issues
Chandra Chekuri
Approximation Algorithms: Load Balancing and Bin Packing
Approximation Algorithms: Load Balancing and Bin Packing
These are lecture notes for a course on approximation algorithms. Chapter 5: Load Balancing and Bin Packing.
0 points
0 issues
A 32-Gb/s NRZ ADC-based SerDes receiver front end is presented in TSMC process. The front end consists of a degenerated CML combined with Gm-TIA Continuous Time Equalizer (CTLE) which provides equalization, gain as well as buffering at , followed by a 32-way time-interleaved Analog-to-Digital Converter (TI-ADC), which is implemented in a hierarchy.
0 points
0 issues
A Review of Trustworthy Graph Learning
A Review of Trustworthy Graph Learning
In this review, we will explore how to develop trustworthy graph neural networks (GNNs) models from different aspects.
26 points
0 issues
How Do We Move Towards True Artificial Intelligence
How Do We Move Towards True Artificial Intelligence
This review discusses the bottleneck challenges experienced in current artificial intelligence research, followed by an analysis of the essence of human intelligence, as well as the differences, advantages, and disadvantages of contemporary machine intelligence and human intelligence and a possible solution towards current problems faced in AI research is suggested.
17 points
0 issues
Bahman Mirheidari
,
André Bittar
,
Nicholas Cummins
,
Johnny Downs
,
Helen L. Fisher
,
Heidi Christensen
Automatic Detection of Expressed Emotion from Five-Minute Speech Samples: Challenges and Opportunities
Automatic Detection of Expressed Emotion from Five-Minute Speech Samples: Challenges and Opportunities
Automatic Detection of Expressed Emotion from Five-Minute Speech Samples: Challenges and Opportunities
2 points
0 issues
Chandra Chekuri
Approximation Algorithms: Packing Problems
Approximation Algorithms: Packing Problems
These are lecture notes for a course on approximation algorithms. Chapter 4: Packing Problems.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Knapsack
Approximation Algorithms: Knapsack
These are lecture notes for a course on approximation algorithms. Chapter 3: Knapsack.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Introduction
Approximation Algorithms: Introduction
These are lecture notes for a course on approximation algorithms. Chapter 1: Introduction.
0 points
0 issues
Chandra Chekuri
Approximation Algorithms: Covering problems
Approximation Algorithms: Covering problems
These are lecture notes for a course on approximation algorithms. Chapter 2: Covering problems.
0 points
0 issues
The set of matrices as a vector space
The set of matrices as a vector space
Definition for the specific case of matrices 2 times 3 of the matrices as a vector space
0 points
0 issues
Find the inverse matrix using Gauss-Jordan method
Find the inverse matrix using Gauss-Jordan method
Here an explanation about how to find the inverse of a matrix using Gauss Jordan method
0 points
0 issues
Chandra Chekuri
\ell_0 sampling, and priority sampling
\ell_0 sampling, and priority sampling
Notes from lecture 9 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Chandra Chekuri
Quantiles and selection in multiple passes
Quantiles and selection in multiple passes
Notes from lecture 10 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Chandra Chekuri
Count and Count-Min Sketches
Count and Count-Min Sketches
Notes from lecture 6 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Chandra Chekuri
Estimating F_2 norm, Sketching, Johnson-Lindenstrauss Lemma
Estimating F_2 norm, Sketching, Johnson-Lindenstrauss Lemma
Notes from lecture 5 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
@Tim.Fahlberg
Using Mathpix and NaviLens to create accessible math flashcards
Using Mathpix and NaviLens to create accessible math flashcards
Students with print disabilities, due to blindness, low vision, learning disabilities or physical disabilities, can greatly benefit from accessible math flashcards and tutorials. MathPix greatly reduces the amount of work required to create these by making quick work of the most time-consuming part of this task by easily capturing text and math from a variety of sources.
11 points
0 issues
Chandra Chekuri
Estimating F_2 norm, Sketching, Johnson-Lindenstrauss Lemma
Estimating F_2 norm, Sketching, Johnson-Lindenstrauss Lemma
Notes from lecture 4 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Chandra Chekuri
Estimating F_k norms via AMS sampling
Estimating F_k norms via AMS sampling
Notes from lecture 3 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Chandra Chekuri
Estimating the Number of Distinct Elements in a Stream
Estimating the Number of Distinct Elements in a Stream
Notes from lecture 2 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Online Publishing Platform, 2010
Online Publishing Platform, 2010
A proposal submitted to (and rejected by) the National Science Foundation in 2010.
1 points
0 issues
Heap sort
Heap sort
This is an article about heap sort, mainly analyzes the heap sort construction process and cost analysis, including the two construction methods of up and down and its algorithm analysis, compared to get a better time complexity construction algorithm, and further reduce the time complexity to make a theoretical analysis.
2 points
0 issues
Chandra Chekuri
Basics of Probability, Probabilistic Counting (Morris's algorithm), and Reservoir Sampling
Basics of Probability, Probabilistic Counting (Morris's algorithm), and Reservoir Sampling
Notes from lecture 1 of Chandra Chekuri's course on algorithms for big data.
0 points
0 issues
Richard Feynman
Introduction to Probability
Introduction to Probability
The true logic of this world is in the calculus of probabilities.
0 points
0 issues
Richard Feynman
The Theory of Gravitation
The Theory of Gravitation
Every object in the universe attracts every other object with a force which for any two bodies is proportional to the mass of each and varies inversely as the square of the distance between them.
0 points
0 issues
Richard Feynman
Introduction to Quantum Behavior
Introduction to Quantum Behavior
“Quantum mechanics” is the description of the behavior of matter in all its details and, in particular, of the happenings on an atomic scale. Things on a very small scale behave like nothing that you have any direct experience about.
0 points
0 issues
@ Samuel Macharia Karimi
Mathematical model of bearing lubrication under themal conditions
Mathematical model of bearing lubrication under themal conditions
The article covers mathematical modelling of bearing lubrication under thermal conditions for rolling bearing.
3 points
0 issues
Christopher Ré
Regularization: Some Calculations from Bias Variance
Regularization: Some Calculations from Bias Variance
These notes contain a reprise of the eigenvalue arguments to understand how variance is reduced by regularization. It also describes different ways regularization can occur including from the algorithm or initialization.
0 points
0 issues
Chuong Do
Introduction to the Multivariate Gaussian Distribution
Introduction to the Multivariate Gaussian Distribution
Notes from Andrew Ng’s CS229 course in Machine Learning about multivariate gaussian distribution.
0 points
0 issues
Andrew Ng
Introduction to Learning Theory
Introduction to Learning Theory
These notes from Andrew Ng’s CS299 course in Machine Learning cover learning theory.
0 points
0 issues
Tengyu Ma
,
Anand Avati
,
Kian Katanforoosh
,
and Andrew Ng
Introduction to Deep Learning
Introduction to Deep Learning
This set of notes gives an overview of neural networks, discusses vectorization and discusses training neural networks with backpropagation. These notes are from Andrew Ng’s famous CS229 course at Stanford.
0 points
0 issues
Yoann Le Calonnec
Introduction to Bias-Variance and Error Analysis
Introduction to Bias-Variance and Error Analysis
Notes on bias-variance and error analysis for students of Andrew Ng’s CS229 course in Machine Learning.
1 points
0 issues
Andrew Ng
Introduction to Reinforcement Learning and Control
Introduction to Reinforcement Learning and Control
These notes from Andrew Ng’s course CS299 cover the topics of reinforcement learning and adaptive control.
0 points
0 issues
Tengyu Ma and Andrew Ng
The Expectation Maximization Algorithm
The Expectation Maximization Algorithm
This set of notes gives a broader view of the EM algorithm, and show how it can be applied to a large family of estimation problems with latent variables.
0 points
0 issues
Mathematical Error In Court Rulings Due To Group Size
Mathematical Error In Court Rulings Due To Group Size
The error in a court ruling composed of a single judge is shown statistically to be 100 percent.
1 points
0 issues
Zico Kolter
,
Chuong Do
,
Tengyu Ma
Linear Algebra Review and Reference for Machine Learning
Linear Algebra Review and Reference for Machine Learning
A review of the concepts of linear algebra for machine learning students of Andrew Ng’s CS229 course at Stanford.
0 points
0 issues
Andrew Ng
Introduction to Principal Components Analysis
Introduction to Principal Components Analysis
These notes develop a method, Principal Components Analysis (PCA), that also tries to identify the subspace in which the data approximately lies.
0 points
0 issues
Andrew Ng
Introduction to Supervised Learning
Introduction to Supervised Learning
The first section of the famous Machine Learning lecture notes from Andrew Ng’s CS229 course at Stanford. The notes cover supervised learning, linear regression, classification and logistic regression, and generalized linear models.
1 points
0 issues
Andrew Ng
Introduction to Kernel Methods
Introduction to Kernel Methods
Notes from Andrew Ng’s CS229 course in Machine Learning about kernal methods and support vector machines.
0 points
0 issues
Andrew Ng
Introduction to Generative Learning Algorithms
Introduction to Generative Learning Algorithms
Andrew Ng’s CS229 lecture notes on generative learning algorithms.
3 points
0 issues
Andrew Ng
Introduction to Independent Components Analysis
Introduction to Independent Components Analysis
Similar to PCA, Independent Component Analysis will find a new basis in which to represent our data. However, the goal is very different.
0 points
0 issues
Andrew Ng
Introduction to Regularization and Model Selection
Introduction to Regularization and Model Selection
Notes from Andrew Ng’s CS229 course in Machine Learning about regularization and model selection.
0 points
0 issues
Andrew Ng
The k-means Clustering Algorithm
The k-means Clustering Algorithm
Notes from Andrew Ng’s CS229 course in Machine Learning about the k-means clustering algorithm.
0 points
0 issues
Satoshi Nakamoto
Bitcoin: A Peer-to-Peer Electronic Cash System
Bitcoin: A Peer-to-Peer Electronic Cash System
The famous whitepaper that introduced the world to a decentralized financial system that eliminated the need for intermediaries.
2 points
0 issues
Jintang Li
This review gives an introduction to Adversarial Machine Learning on graph-structured data, including several recent papers and research ideas in this field. This review is based on our paper “A Survey of Adversarial Learning on Graph”.
5 points
0 issues
Gabriel McRae
Denoising ultra-high resolution cryo-electron tomograms
Denoising ultra-high resolution cryo-electron tomograms
Cryo-electron microscopy allows researchers to investigate the mechanisms of cells at detail in the Angstrom range, even enabling the visualization of single atoms in molecular machines frozen in their native states. However, as samples become more complex, so does data analysis, and the crowded molecular environment is extremely difficult to interpret. Denoising algorithms based on Noise2Noise show great promise in visualizing detail, and this brief review will aim to introduce the state of the art in denoising of 3-dimensional image volumes of cellular samples at ultra-high resolution.
5 points
0 issues
Andrew Ng
Mixtures of Gaussians and the EM algorithm
Mixtures of Gaussians and the EM algorithm
These notes from Andrew Ng’s CS229 course in Machine Learning discuss the EM (Expectation-Maximization) algorithm for density estimation.
0 points
0 issues
Nickil Maveli
Demystifying Post-hoc Explainability for ML models
Demystifying Post-hoc Explainability for ML models
The widespread use of black-box models in AI has increased the need for explanation methods that reveal how these mysterious models arrive at concrete decisions. We will describe the problem, prominent solutions, and example applications for each of these approaches, as well as their vulnerabilities and flaws. We hope to have a enriching and an informative introduction to post-hoc machine learning explainability.
2 points
0 issues
Chuong Do
More on Multivariate Gaussians
More on Multivariate Gaussians
Notes from Andrew Ng’s CS229 course in Machine Learning about multivariate gaussian distribution continued.
0 points
0 issues
Arian Maleki and Tom Do
Review of Probability Theory
Review of Probability Theory
Probability theory is the study of uncertainty. These notes attempt to cover the basics of probability theory at a level appropriate for Andrew Ng’s CS229 course in Machine Learning.
0 points
0 issues
Oles Matsyshyn$^{1}$
,
Urmimala Dey$^{1 , 3}$
,
Inti Sodemann$^{1}$
,
Yan Sun$^{2}$
The Berry Phase Rectification Tensor and The Solar Rectification Vector
The Berry Phase Rectification Tensor and The Solar Rectification Vector
We introduce an operational definition of the Berry Phase Rectification Tensor as the second order change of polarization of a material in response to an ideal short pulse of electric field. Under time reversal symmetry this tensor depends exclusively on the Berry phases of the Bloch bands and not on their energy dispersions, making it an intrinsic property to each material which contains contributions from both the inter-band shift currents and the intra-band Berry Curvature Dipole. We also introduce the Solar Rectification Vector as a technologically relevant figure of merit for bulk photo-current generation which counts the number of electrons contributing to the rectified current per incoming photon under ideal black-body radiation in analogy with the classic solar cell model of Shockley and Queisser.
0 points
1 issues
David McCaffary
Towards continual task learning in artificial neural networks
Towards continual task learning in artificial neural networks
Critical appraisal of prominent current approaches to alleviating catastrophic forgetting in neural networks, drawing on inspiration from neuroscience.
3 points
0 issues
Co-Tuning: An easy but effective trick to improve transfer learning
Co-Tuning: An easy but effective trick to improve transfer learning
Transfer learning is a popular method in the deep learning community, but it is usually implemented naively (eg. copying weights as initialization). Co-Tuning is a recently proposed technique to improve transfer learning that is easy to implement, and effective to a wide variety of tasks.
4 points
0 issues
Christopher Dzuwa
Knowledge evolution in neural networks
Knowledge evolution in neural networks
Deep learning relies on the availability of a large corpus of data (labeled or unlabeled). Thus, one challenging unsettled question is: how to train a deep network on a relatively small dataset? To tackle this question, Ahmed Taha, Abhinav Shrivastava, Larry Davis proposed an evolution-inspired training approach to boost performance on relatively small datasets. This article gives a detailed summary of their paper, “Knowledge evolution in neural networks”
2 points
0 issues
Pierre Orhan
Advances in machine learning using geometry provide new tools for computational neuroscientist
Advances in machine learning using geometry provide new tools for computational neuroscientist
A geometrical perspective proves efficient in developing machine learning tools for computational neuroscience.
2 points
0 issues
Anish Ghosh
,
Bivek Panthi
,
Sishir Sunar
Recognition of Hand Written Mathematical Expression using Scale Augmentation and Drop Attention
Recognition of Hand Written Mathematical Expression using Scale Augmentation and Drop Attention
We start by explaining about how handwritten mathematical expressions have unstable scale. Then we show how augmented layers are used for scaling those mathematical expression. We continue by explaining how an attention based encoder-decoder is used for extracting features and generating predictions. The drop attention is used when the attention distribution of the decoder is not precise. This method achieves better performance than any other existing method.
1 points
0 issues
Veronika Samborska
Adversarial attacks in deep learning: what can they teach us?
Adversarial attacks in deep learning: what can they teach us?
Review of the major studies discussing adversarial attacks and defences
2 points
0 issues
Rachel Wang
Machine-learning Online Optimisation for Evaporative Cooling in Cold-atom Experiments
Machine-learning Online Optimisation for Evaporative Cooling in Cold-atom Experiments
As quantum systems become increasingly complex, optimisation algorithms are becoming a requirement for high-precision experiments. Machine-learning online optimisation offers an alternative to theoretical models, relying instead on experimental observations to continuously update an internal surrogate model. Two online optimisation techniques are reviewed in this paper in the context of evaporative cooling for the efficient and high-quality production of Bose-Einstein condensates (BEC). These two methods prioritise different stages of cooling with one focused on optimising experimental settings and the other on improving image acquisition.
0 points
0 issues
Roman Böhringer
Causal Machine Learning in Healthcare
Causal Machine Learning in Healthcare
This review gives an introduction to Causal Machine Learning with a focus on healthcare and the issues that are faced there. Several recent papers and research ideas in this area are presented.
0 points
0 issues
That's everything! Take me back to the top.