The model development two objectives are:
1) To explain home prices using demographic explanatory variables; and
2) To benchmark the accuracy of OLS regressions vs. DNN models.
For home prices, we used county level data from Zillow. For the explanatory variables, we used data from GEOFRED.
We will test whether :
a) Sequential Deep Neural Networks (DNNs) can predict the stock market (S&P 500) better than OLS regression;
b) DNNs using smooth Rectified Linear activation functions perform better than the ones using Sigmoid (Logit) activation functions.
An introductory/illustrative but precise slide on mathematics on neural networks (densely connected layers).
Please download it and see its animations with PowerPoint.
*This slide is not finished yet. If you like it, please give me some feedback to motivate me.
I made this slide as an intern in DATANOMIQ Gmbh
URL: https://www.datanomiq.de/
Customer Churn is a burning problem for Telecom companies. In this project, we simulate one such case of customer churn where we work on a data of postpaid customers with a contract. The data has information about the customer usage behavior, contract details and the payment details. The data also indicates which were the customers who canceled their service. Based on this past data, we need to build a model which can predict whether a customer will cancel their service in the future or not.
A simple framework for contrastive learning of visual representationsDevansh16
Link: https://machine-learning-made-simple.medium.com/learnings-from-simclr-a-framework-contrastive-learning-for-visual-representations-6c145a5d8e99
If you'd like to discuss something, text me on LinkedIn, IG, or Twitter. To support me, please use my referral link to Robinhood. It's completely free, and we both get a free stock. Not using it is literally losing out on free money.
Check out my other articles on Medium. : https://rb.gy/zn1aiu
My YouTube: https://rb.gy/88iwdd
Reach out to me on LinkedIn. Let's connect: https://rb.gy/m5ok2y
My Instagram: https://rb.gy/gmvuy9
My Twitter: https://twitter.com/Machine01776819
My Substack: https://devanshacc.substack.com/
Live conversations at twitch here: https://rb.gy/zlhk9y
Get a free stock on Robinhood: https://join.robinhood.com/fnud75
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.
Comments: ICML'2020. Code and pretrained models at this https URL
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
Cite as: arXiv:2002.05709 [cs.LG]
(or arXiv:2002.05709v3 [cs.LG] for this version)
Submission history
From: Ting Chen [view email]
[v1] Thu, 13 Feb 2020 18:50:45 UTC (5,093 KB)
[v2] Mon, 30 Mar 2020 15:32:51 UTC (5,047 KB)
[v3] Wed, 1 Jul 2020 00:09:08 UTC (5,829 KB)
We will test whether :
a) Sequential Deep Neural Networks (DNNs) can predict the stock market (S&P 500) better than OLS regression;
b) DNNs using smooth Rectified Linear activation functions perform better than the ones using Sigmoid (Logit) activation functions.
An introductory/illustrative but precise slide on mathematics on neural networks (densely connected layers).
Please download it and see its animations with PowerPoint.
*This slide is not finished yet. If you like it, please give me some feedback to motivate me.
I made this slide as an intern in DATANOMIQ Gmbh
URL: https://www.datanomiq.de/
Customer Churn is a burning problem for Telecom companies. In this project, we simulate one such case of customer churn where we work on a data of postpaid customers with a contract. The data has information about the customer usage behavior, contract details and the payment details. The data also indicates which were the customers who canceled their service. Based on this past data, we need to build a model which can predict whether a customer will cancel their service in the future or not.
A simple framework for contrastive learning of visual representationsDevansh16
Link: https://machine-learning-made-simple.medium.com/learnings-from-simclr-a-framework-contrastive-learning-for-visual-representations-6c145a5d8e99
If you'd like to discuss something, text me on LinkedIn, IG, or Twitter. To support me, please use my referral link to Robinhood. It's completely free, and we both get a free stock. Not using it is literally losing out on free money.
Check out my other articles on Medium. : https://rb.gy/zn1aiu
My YouTube: https://rb.gy/88iwdd
Reach out to me on LinkedIn. Let's connect: https://rb.gy/m5ok2y
My Instagram: https://rb.gy/gmvuy9
My Twitter: https://twitter.com/Machine01776819
My Substack: https://devanshacc.substack.com/
Live conversations at twitch here: https://rb.gy/zlhk9y
Get a free stock on Robinhood: https://join.robinhood.com/fnud75
This paper presents SimCLR: a simple framework for contrastive learning of visual representations. We simplify recently proposed contrastive self-supervised learning algorithms without requiring specialized architectures or a memory bank. In order to understand what enables the contrastive prediction tasks to learn useful representations, we systematically study the major components of our framework. We show that (1) composition of data augmentations plays a critical role in defining effective predictive tasks, (2) introducing a learnable nonlinear transformation between the representation and the contrastive loss substantially improves the quality of the learned representations, and (3) contrastive learning benefits from larger batch sizes and more training steps compared to supervised learning. By combining these findings, we are able to considerably outperform previous methods for self-supervised and semi-supervised learning on ImageNet. A linear classifier trained on self-supervised representations learned by SimCLR achieves 76.5% top-1 accuracy, which is a 7% relative improvement over previous state-of-the-art, matching the performance of a supervised ResNet-50. When fine-tuned on only 1% of the labels, we achieve 85.8% top-5 accuracy, outperforming AlexNet with 100X fewer labels.
Comments: ICML'2020. Code and pretrained models at this https URL
Subjects: Machine Learning (cs.LG); Computer Vision and Pattern Recognition (cs.CV); Machine Learning (stat.ML)
Cite as: arXiv:2002.05709 [cs.LG]
(or arXiv:2002.05709v3 [cs.LG] for this version)
Submission history
From: Ting Chen [view email]
[v1] Thu, 13 Feb 2020 18:50:45 UTC (5,093 KB)
[v2] Mon, 30 Mar 2020 15:32:51 UTC (5,047 KB)
[v3] Wed, 1 Jul 2020 00:09:08 UTC (5,829 KB)
We propose an algorithm for training Multi Layer Preceptrons for classification problems, that we named Hidden Layer Learning Vector Quantization (H-LVQ). It consists of applying Learning Vector Quantization to the last hidden layer of a MLP and it gave very successful results on problems containing a large number of correlated inputs. It was applied with excellent results on classification of Rurtherford
backscattering spectra and on a benchmark problem of image recognition. It may also be used for efficient feature extraction.
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCOREIJCI JOURNAL
Text generation using GAN networks is becoming more effective but still requires new approaches to
achieve stable training and controlled output. Applying feedback score to control text generation is one of
the most important topics in NLP nowadays. Feedback or response is a natural part of conversations and
not only consists of words, but also can take other shapes such as emotions, or other reactions. In dialogue
processes feedback is a factor influencing the next phrase or reaction. Depending on this feedback or
response we correct our possible answers by trying to change the tone, context, or even structure of the
sentences. Applying feedback as part of the GAN model structure will give us new ways to apply feedback
and generate well-controlled outputs with defined scores which is very important in real-world
applications and systems. With GAN networks and their instability in training and unique architecture, it
becomes trickier and requires new ways of solving this problem. The matter of feedback usages for text
generation task using GAN networks we will review in this paper and experiment with integrating score
values into GAN's generator model layers.
EFFICIENT KNOWLEDGE BASE MANAGEMENT IN DCSP ijasuc
DCSP (Distributed Constraint Satisfaction Problem) has been a very important research area in AI
(Artificial Intelligence). There are many application problems in distributed AI that can be formalized as
DSCPs. With the increasing complexity and problem size of the application problems in AI, the required
storage place in searching and the average searching time are increasing too. Thus, to use a limited
storage place efficiently in solving DCSP becomes a very important problem, and it can help to reduce
searching time as well. This paper provides an efficient knowledge base management approach based on
general usage of hyper-resolution-rule in consistence algorithm. The approach minimizes the increasing of
the knowledge base by eliminate sufficient constraint and false nogood. These eliminations do not change
the completeness of the original knowledge base increased. The proofs are given as well. The example
shows that this approach decrease both the new nogoods generated and the knowledge base greatly. Thus
it decreases the required storage place and simplify the searching process.
Regularization why you should avoid themGaetan Lion
Regularization models are supposed to reduce model over-fitting and improve forecasting accuracy. Very often they do just the opposite: increase model under-fitting, and decrease model forecasting accuracy. This study explains how Regularization models often fail, and how to resolve model issues with far simpler and more robust methods.
Improving Hardware Efficiency for DNN ApplicationsChester Chen
Speaker: Dr. Hai (Helen) Li is the Clare Boothe Luce Associate Professor of Electrical and Computer Engineering and Co-director of the Duke Center for Evolutionary Intelligence at Duke University
In this talk, I will introduce a few recent research spotlights by the Duke Center for Evolutionary Intelligence. The talk will start with the structured sparsity learning (SSL) method which attempts to learn a compact structure from a bigger DNN to reduce computation cost. It generates a regularized structure with high execution efficiency. Our experiments on CPU, GPU, and FPGA platforms show on average 3~5 times speedup of convolutional layer computation of AlexNet. Then, the implementation and acceleration of DNN applications on mobile computing systems will be introduced. MoDNN is a local distributed system which partitions DNN models onto several mobile devices to accelerate computations. ApesNet is an efficient pixel-wise segmentation network, which understands road scenes in real-time, and has achieved promising accuracy. Our prospects on the adoption of emerging technology will also be given at the end of this talk, offering the audiences an alternative thinking about the future evolution and revolution of modern computing systems.
Constructing a classification model is important in machine learning for a particular task. A
classification process involves assigning objects into predefined groups or classes based on a
number of observed attributes related to those objects. Artificial neural network is one of the
classification algorithms which, can be used in many application areas. This paper investigates
the potential of applying the feed forward neural network architecture for the classification of
medical datasets. Migration based differential evolution algorithm (MBDE) is chosen and
applied to feed forward neural network to enhance the learning process and the network
learning is validated in terms of convergence rate and classification accuracy. In this paper,
MBDE algorithm with various migration policies is proposed for classification problems using
medical diagnosis.
MEDICAL DIAGNOSIS CLASSIFICATION USING MIGRATION BASED DIFFERENTIAL EVOLUTION...cscpconf
Constructing a classification model is important in machine learning for a particular task. A
classification process involves assigning objects into predefined groups or classes based on a
number of observed attributes related to those objects. Artificial neural network is one of the
classification algorithms which, can be used in many application areas. This paper investigates
the potential of applying the feed forward neural network architecture for the classification of
medical datasets. Migration based differential evolution algorithm (MBDE) is chosen and
applied to feed forward neural network to enhance the learning process and the network
learning is validated in terms of convergence rate and classification accuracy. In this paper,
MBDE algorithm with various migration policies is proposed for classification problems using
medical diagnosis.
Identifying Critical Neurons in ANN Architectures using Mixed Integer Program...Mostafa ElAraby
We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in
deep neural network architectures which are guided by the impact of their simultaneous pruning
on the main learning task of the network. By carefully devising the objective function of the MIP,
we drive the solver to minimize the number of critical neurons (i.e., with high importance score)
that need to be kept for maintaining the overall accuracy of the trained neural network. Further, the
proposed formulation generalizes the recently considered lottery ticket optimization by identifying multiple “lucky” sub-networks resulting in optimized architecture that not only performs well
on a single dataset, but also generalizes across multiple ones upon retraining of network weights.
Presented in this document is a short description of a straightforward and effective technique to help diagnose infeasibilities in IMPL (Industrial Modeling and Programming Language). IMPL is mathematical programming based where many previous and useful studies on infeasibility diagnosis have been published (Greenberg, 1993; Chinneck, 1993; Chinneck, 2008). It is generally accepted that the “Irreducible Infeasibility Sets (IIS)” developed by Chinneck (1993) is a useful approach to diagnosing infeasibilities and can be found in all commercial LP-based solvers such as CPLEX, GUROBI and XPRESS. Unfortunately IIS performed on industrial optimization problems (IOP) is both slow and difficult to interpret especially for the end-user given that a plethora of IIS’s can be generated with little perceived connection between the variables or constraints contained in them.
Another useful and extensively implemented approach that can also be helpful in diagnosing infeasibilities in the linear part of either the MILP or NLP is the presolving or preprocessing techniques found in for example Fourer and Gay (1993) and Andersen and Andersen (1995). These are extremely powerful to reduce the size and in some cases the complexity of the matrix that is ultimately transferred to the LP, QP, MILP or SLP. Unfortunately, although they can quickly and accurately detect LP infeasibilities, they provide little information to aid in the infeasibility diagnosis (Chinneck, 2008) as well shall see later.
Instead, IMPL uses a well-known “tightening” technique to analyze the problem by focusing on the quantity phenomenon first given that it is our experience that in IOP’s, a great majority or percentage of the infeasibilities occur in this dimension. This is fortunate given that the constraints are linear in the variables and we can solve many LP’s rapidly as specialized network-flow problems where the dual simplex LP method is particularly efficient and if required we can solve several LP’s in-parallel.
Essentially, we have two types of infeasibilities in IOP’s i.e., “incomplete” and “inconsistent” models. Incomplete models are problems where we expect to solve the problem when the problem is ill-defined or insufficiently specified. Inconsistent models are problems where some parts of the problem are incongruent, misaligned or contradictory with other parts.
An Improved Differential Evolution Algorithm for Real Parameter Optimization ...IDES Editor
Differential Evolution (DE) is a powerful yet simple
evolutionary algorithm for optimization of real valued, multi
modal functions. DE is generally considered as a reliable,
accurate and robust optimization technique. However, the
algorithm suffers from premature convergence, slow
convergence rate and large computational time for optimizing
the computationally expensive objective functions. Therefore,
an attempt to speed up DE is considered necessary. This paper
introduces an improved differential evolution (IDE), a
modification to DE that enhances the convergence rate without
compromising with the solution quality. In improved
differential evolution (IDE) algorithm, initial population of
individual is partitioned into several sub-populations, and then
DE algorithm which utilize only one set of population instead
of two as in original DE, is applied to each sub-population
independently. At periodic stages in evolution, the entire
population is shuffled, and then points are reassigned to subpopulations.
The performance of IDE on a test bed of functions
is compared with original DE. It is found that IDE requires
less computational effort to locate global optimal solution.
Sacramento's population projections for the State of California are already 1.4 million too high only 3 years into the forecast by 2023. The reason is Sacramento's unrealistic migration assumption. This analysis tests in detail how and why this projection went so wrong.
This study analyzes the temperature history of 24 American cities going back to 1895. Using a LOESS model, it forecasts prospective temperature increases over the next 40 years and out to 2100. And, it compares the 2100 forecast with the NOAA model(s). This comparison uncovers serious deficiencies within the NOAA model(s), as it does not fit the historical data well; and it does not differentiate much forecasts between various cities.
We propose an algorithm for training Multi Layer Preceptrons for classification problems, that we named Hidden Layer Learning Vector Quantization (H-LVQ). It consists of applying Learning Vector Quantization to the last hidden layer of a MLP and it gave very successful results on problems containing a large number of correlated inputs. It was applied with excellent results on classification of Rurtherford
backscattering spectra and on a benchmark problem of image recognition. It may also be used for efficient feature extraction.
TEXT GENERATION WITH GAN NETWORKS USING FEEDBACK SCOREIJCI JOURNAL
Text generation using GAN networks is becoming more effective but still requires new approaches to
achieve stable training and controlled output. Applying feedback score to control text generation is one of
the most important topics in NLP nowadays. Feedback or response is a natural part of conversations and
not only consists of words, but also can take other shapes such as emotions, or other reactions. In dialogue
processes feedback is a factor influencing the next phrase or reaction. Depending on this feedback or
response we correct our possible answers by trying to change the tone, context, or even structure of the
sentences. Applying feedback as part of the GAN model structure will give us new ways to apply feedback
and generate well-controlled outputs with defined scores which is very important in real-world
applications and systems. With GAN networks and their instability in training and unique architecture, it
becomes trickier and requires new ways of solving this problem. The matter of feedback usages for text
generation task using GAN networks we will review in this paper and experiment with integrating score
values into GAN's generator model layers.
EFFICIENT KNOWLEDGE BASE MANAGEMENT IN DCSP ijasuc
DCSP (Distributed Constraint Satisfaction Problem) has been a very important research area in AI
(Artificial Intelligence). There are many application problems in distributed AI that can be formalized as
DSCPs. With the increasing complexity and problem size of the application problems in AI, the required
storage place in searching and the average searching time are increasing too. Thus, to use a limited
storage place efficiently in solving DCSP becomes a very important problem, and it can help to reduce
searching time as well. This paper provides an efficient knowledge base management approach based on
general usage of hyper-resolution-rule in consistence algorithm. The approach minimizes the increasing of
the knowledge base by eliminate sufficient constraint and false nogood. These eliminations do not change
the completeness of the original knowledge base increased. The proofs are given as well. The example
shows that this approach decrease both the new nogoods generated and the knowledge base greatly. Thus
it decreases the required storage place and simplify the searching process.
Regularization why you should avoid themGaetan Lion
Regularization models are supposed to reduce model over-fitting and improve forecasting accuracy. Very often they do just the opposite: increase model under-fitting, and decrease model forecasting accuracy. This study explains how Regularization models often fail, and how to resolve model issues with far simpler and more robust methods.
Improving Hardware Efficiency for DNN ApplicationsChester Chen
Speaker: Dr. Hai (Helen) Li is the Clare Boothe Luce Associate Professor of Electrical and Computer Engineering and Co-director of the Duke Center for Evolutionary Intelligence at Duke University
In this talk, I will introduce a few recent research spotlights by the Duke Center for Evolutionary Intelligence. The talk will start with the structured sparsity learning (SSL) method which attempts to learn a compact structure from a bigger DNN to reduce computation cost. It generates a regularized structure with high execution efficiency. Our experiments on CPU, GPU, and FPGA platforms show on average 3~5 times speedup of convolutional layer computation of AlexNet. Then, the implementation and acceleration of DNN applications on mobile computing systems will be introduced. MoDNN is a local distributed system which partitions DNN models onto several mobile devices to accelerate computations. ApesNet is an efficient pixel-wise segmentation network, which understands road scenes in real-time, and has achieved promising accuracy. Our prospects on the adoption of emerging technology will also be given at the end of this talk, offering the audiences an alternative thinking about the future evolution and revolution of modern computing systems.
Constructing a classification model is important in machine learning for a particular task. A
classification process involves assigning objects into predefined groups or classes based on a
number of observed attributes related to those objects. Artificial neural network is one of the
classification algorithms which, can be used in many application areas. This paper investigates
the potential of applying the feed forward neural network architecture for the classification of
medical datasets. Migration based differential evolution algorithm (MBDE) is chosen and
applied to feed forward neural network to enhance the learning process and the network
learning is validated in terms of convergence rate and classification accuracy. In this paper,
MBDE algorithm with various migration policies is proposed for classification problems using
medical diagnosis.
MEDICAL DIAGNOSIS CLASSIFICATION USING MIGRATION BASED DIFFERENTIAL EVOLUTION...cscpconf
Constructing a classification model is important in machine learning for a particular task. A
classification process involves assigning objects into predefined groups or classes based on a
number of observed attributes related to those objects. Artificial neural network is one of the
classification algorithms which, can be used in many application areas. This paper investigates
the potential of applying the feed forward neural network architecture for the classification of
medical datasets. Migration based differential evolution algorithm (MBDE) is chosen and
applied to feed forward neural network to enhance the learning process and the network
learning is validated in terms of convergence rate and classification accuracy. In this paper,
MBDE algorithm with various migration policies is proposed for classification problems using
medical diagnosis.
Identifying Critical Neurons in ANN Architectures using Mixed Integer Program...Mostafa ElAraby
We introduce a mixed integer program (MIP) for assigning importance scores to each neuron in
deep neural network architectures which are guided by the impact of their simultaneous pruning
on the main learning task of the network. By carefully devising the objective function of the MIP,
we drive the solver to minimize the number of critical neurons (i.e., with high importance score)
that need to be kept for maintaining the overall accuracy of the trained neural network. Further, the
proposed formulation generalizes the recently considered lottery ticket optimization by identifying multiple “lucky” sub-networks resulting in optimized architecture that not only performs well
on a single dataset, but also generalizes across multiple ones upon retraining of network weights.
Presented in this document is a short description of a straightforward and effective technique to help diagnose infeasibilities in IMPL (Industrial Modeling and Programming Language). IMPL is mathematical programming based where many previous and useful studies on infeasibility diagnosis have been published (Greenberg, 1993; Chinneck, 1993; Chinneck, 2008). It is generally accepted that the “Irreducible Infeasibility Sets (IIS)” developed by Chinneck (1993) is a useful approach to diagnosing infeasibilities and can be found in all commercial LP-based solvers such as CPLEX, GUROBI and XPRESS. Unfortunately IIS performed on industrial optimization problems (IOP) is both slow and difficult to interpret especially for the end-user given that a plethora of IIS’s can be generated with little perceived connection between the variables or constraints contained in them.
Another useful and extensively implemented approach that can also be helpful in diagnosing infeasibilities in the linear part of either the MILP or NLP is the presolving or preprocessing techniques found in for example Fourer and Gay (1993) and Andersen and Andersen (1995). These are extremely powerful to reduce the size and in some cases the complexity of the matrix that is ultimately transferred to the LP, QP, MILP or SLP. Unfortunately, although they can quickly and accurately detect LP infeasibilities, they provide little information to aid in the infeasibility diagnosis (Chinneck, 2008) as well shall see later.
Instead, IMPL uses a well-known “tightening” technique to analyze the problem by focusing on the quantity phenomenon first given that it is our experience that in IOP’s, a great majority or percentage of the infeasibilities occur in this dimension. This is fortunate given that the constraints are linear in the variables and we can solve many LP’s rapidly as specialized network-flow problems where the dual simplex LP method is particularly efficient and if required we can solve several LP’s in-parallel.
Essentially, we have two types of infeasibilities in IOP’s i.e., “incomplete” and “inconsistent” models. Incomplete models are problems where we expect to solve the problem when the problem is ill-defined or insufficiently specified. Inconsistent models are problems where some parts of the problem are incongruent, misaligned or contradictory with other parts.
An Improved Differential Evolution Algorithm for Real Parameter Optimization ...IDES Editor
Differential Evolution (DE) is a powerful yet simple
evolutionary algorithm for optimization of real valued, multi
modal functions. DE is generally considered as a reliable,
accurate and robust optimization technique. However, the
algorithm suffers from premature convergence, slow
convergence rate and large computational time for optimizing
the computationally expensive objective functions. Therefore,
an attempt to speed up DE is considered necessary. This paper
introduces an improved differential evolution (IDE), a
modification to DE that enhances the convergence rate without
compromising with the solution quality. In improved
differential evolution (IDE) algorithm, initial population of
individual is partitioned into several sub-populations, and then
DE algorithm which utilize only one set of population instead
of two as in original DE, is applied to each sub-population
independently. At periodic stages in evolution, the entire
population is shuffled, and then points are reassigned to subpopulations.
The performance of IDE on a test bed of functions
is compared with original DE. It is found that IDE requires
less computational effort to locate global optimal solution.
Sacramento's population projections for the State of California are already 1.4 million too high only 3 years into the forecast by 2023. The reason is Sacramento's unrealistic migration assumption. This analysis tests in detail how and why this projection went so wrong.
This study analyzes the temperature history of 24 American cities going back to 1895. Using a LOESS model, it forecasts prospective temperature increases over the next 40 years and out to 2100. And, it compares the 2100 forecast with the NOAA model(s). This comparison uncovers serious deficiencies within the NOAA model(s), as it does not fit the historical data well; and it does not differentiate much forecasts between various cities.
Compact Letter Display (CLD). How it worksGaetan Lion
Compact Letter Display (CLD) renders ANOVA & Tukey HSD testing a lot easier to interpret. It readily ranks and differentiate the tested variables. With CLD you can readily identify the variables that are statistically dissimilar vs. the ones that are similar.
This study compares the benefits and the funding for CalPERS pensions vs. Social Security. It also looks in more detail on the financial burden of CalPERS pensions on the Marin Municipal Water District.
This presentation includes two explanatory models to attempt to predict recessions. The first one is a logistic regression. The second one is a deep neural network (DNN). Both use the same set of independent variables: the velocity of money, inflation, the yield curve, and the stock market. As usual, the DNN fits the historical data a bit better than the simpler logistic regression. But, when it comes to testing or predicting, both models are pretty much even.
Objective:
Studying trends in US inequality along several social dimensions including education, ethnicity, percentiles, and work status. We don’t explore gender because it is not disaggregated within the mentioned data that focuses on families (fairly similar to households).
Data source:
US Government Survey of Consumer Finance (SCF) data. The SCF aggregates financial data on US families every three years. And, it discloses a time series from 1989 to 2019.
This analysis focuses on population aging, population age categories in % (age pyramids), and overall population growth. It looks at various geographic units (countries, continents, regions, World) from 1950 to the Present (2019 & 2020). And, it looks at projections out to 2100.
Africa is an outlier to the overall global aging; its population growth (historical & projected) is far faster than for other major regions.
We are going to analyze several of the major cryptocurrencies as an asset class. And, we are going to address several related questions:
Do they provide diversification benefits relative to the stock market (S&P 500)?
How do their diversification benefits compare with Gold’s diversification benefit vs. the stock market?
Do cryptocurrencies provide diversification benefits when you really need it… during market downturns?
Are cryptocurrencies truly “digital Gold”? Do they behave in a similar way given that their supply is constrained (supposedly in a similar way as Gold is)?
Can Treasury Inflation Protected Securities predict Inflation?Gaetan Lion
We look at the spread between Treasuries and TIPS to figure out how effective such observations were in predicting actual inflation several years down the road.
This analysis focuses on measures much beyond PE ratios. And, it concludes that the Stock Market is actually really cheap vs. bonds. But, it appears quite overvalued when focusing on inflation measures.
The relationship between the Stock Market and Interest RatesGaetan Lion
This is a study of the relationship between the Stock Market and Interest Rates. We review how the Stock Market has reacted when interest rates rise. We also factor the influence of other macroeconomics variables.
This is a study using historical data and forecasts of life expectancy for several countries. The data and forecasts come from the UN - Population Division. While the historical data is most interesting, the forecasts are highly optimistic as they project a linear trend way into the future. Meanwhile, those forecasts should have followed a much more realistic logarithmic curve reflecting slower increase in life expectancy as the life expectancy rises.
Will Stock Markets survive in 200 years?Gaetan Lion
This study uncovers 11 international stock markets that are already running into existing and prospective demographic and economic growth constraints. This study evaluates their respective fragile long term viability and the implications this has for the investors in such countries.
This study answers three questions:
1) Does it make a difference whether you standardize your variables before running your model or standardize the regression coefficients after you run your model?
2) Does the scale of the respective original non-standardized variables affect the resulting standardized coefficients?
3) Does using non-standardized variables vs. standardized variables have an impact when conducting regularization (Ridge Regression, LASSO)?
This analysis compares his track record vs. Manning, Montana, Marino, Brees, Favre, and Elway. At the end of this analysis, it makes extensive use of the binomial distribution to figure out how much of their respective track records are due to randomness vs. skills.
This study reviews the increasing prevalence of 3-shot points within the NBA. It also compares the record of the 5 top players in NBA history in 3-pt shots. It also considers how many good years left Curry may have.
Japan vs. US comparison on numerous dimensionsGaetan Lion
This study compares Japan vs. the US on numerous dimensions including demographics (including health and education), and economics (including monetary and fiscal policies). This is to observe when Japan and the US trends are likely to converge over time.
Climate change model forecast global temperature out to 2100Gaetan Lion
This study is leveraging a VAR model introduced in an earlier presentation to forecast global temperature out to 2100, and assess how likely are we to keep such temperatures at or under the + 1.5 degree Celsius threshold.
This study consist in:
1) First, reviewing the historical data of the World population and economic growth over the past several centuries;
2) Second, envisioning what our future over the next several centuries may look like, while assessing scenarios feasibility; and
3) Looking at recent trends over the past several decades.
The Evolution of Non-Banking Financial Companies (NBFCs) in India: Challenges...beulahfernandes8
Role in Financial System
NBFCs are critical in bridging the financial inclusion gap.
They provide specialized financial services that cater to segments often neglected by traditional banks.
Economic Impact
NBFCs contribute significantly to India's GDP.
They support sectors like micro, small, and medium enterprises (MSMEs), housing finance, and personal loans.
BYD SWOT Analysis and In-Depth Insights 2024.pptxmikemetalprod
Indepth analysis of the BYD 2024
BYD (Build Your Dreams) is a Chinese automaker and battery manufacturer that has snowballed over the past two decades to become a significant player in electric vehicles and global clean energy technology.
This SWOT analysis examines BYD's strengths, weaknesses, opportunities, and threats as it competes in the fast-changing automotive and energy storage industries.
Founded in 1995 and headquartered in Shenzhen, BYD started as a battery company before expanding into automobiles in the early 2000s.
Initially manufacturing gasoline-powered vehicles, BYD focused on plug-in hybrid and fully electric vehicles, leveraging its expertise in battery technology.
Today, BYD is the world’s largest electric vehicle manufacturer, delivering over 1.2 million electric cars globally. The company also produces electric buses, trucks, forklifts, and rail transit.
On the energy side, BYD is a major supplier of rechargeable batteries for cell phones, laptops, electric vehicles, and energy storage systems.
what is the best method to sell pi coins in 2024DOT TECH
The best way to sell your pi coins safely is trading with an exchange..but since pi is not launched in any exchange, and second option is through a VERIFIED pi merchant.
Who is a pi merchant?
A pi merchant is someone who buys pi coins from miners and pioneers and resell them to Investors looking forward to hold massive amounts before mainnet launch in 2026.
I will leave the telegram contact of my personal pi merchant to trade pi coins with.
@Pi_vendor_247
how to sell pi coins in South Korea profitably.DOT TECH
Yes. You can sell your pi network coins in South Korea or any other country, by finding a verified pi merchant
What is a verified pi merchant?
Since pi network is not launched yet on any exchange, the only way you can sell pi coins is by selling to a verified pi merchant, and this is because pi network is not launched yet on any exchange and no pre-sale or ico offerings Is done on pi.
Since there is no pre-sale, the only way exchanges can get pi is by buying from miners. So a pi merchant facilitates these transactions by acting as a bridge for both transactions.
How can i find a pi vendor/merchant?
Well for those who haven't traded with a pi merchant or who don't already have one. I will leave the telegram id of my personal pi merchant who i trade pi with.
Tele gram: @Pi_vendor_247
#pi #sell #nigeria #pinetwork #picoins #sellpi #Nigerian #tradepi #pinetworkcoins #sellmypi
how can i use my minded pi coins I need some funds.DOT TECH
If you are interested in selling your pi coins, i have a verified pi merchant, who buys pi coins and resell them to exchanges looking forward to hold till mainnet launch.
Because the core team has announced that pi network will not be doing any pre-sale. The only way exchanges like huobi, bitmart and hotbit can get pi is by buying from miners.
Now a merchant stands in between these exchanges and the miners. As a link to make transactions smooth. Because right now in the enclosed mainnet you can't sell pi coins your self. You need the help of a merchant,
i will leave the telegram contact of my personal pi merchant below. 👇 I and my friends has traded more than 3000pi coins with him successfully.
@Pi_vendor_247
Introduction to Indian Financial System ()Avanish Goel
The financial system of a country is an important tool for economic development of the country, as it helps in creation of wealth by linking savings with investments.
It facilitates the flow of funds form the households (savers) to business firms (investors) to aid in wealth creation and development of both the parties
Currently pi network is not tradable on binance or any other exchange because we are still in the enclosed mainnet.
Right now the only way to sell pi coins is by trading with a verified merchant.
What is a pi merchant?
A pi merchant is someone verified by pi network team and allowed to barter pi coins for goods and services.
Since pi network is not doing any pre-sale The only way exchanges like binance/huobi or crypto whales can get pi is by buying from miners. And a merchant stands in between the exchanges and the miners.
I will leave the telegram contact of my personal pi merchant. I and my friends has traded more than 6000pi coins successfully
Tele-gram
@Pi_vendor_247
Empowering the Unbanked: The Vital Role of NBFCs in Promoting Financial Inclu...Vighnesh Shashtri
In India, financial inclusion remains a critical challenge, with a significant portion of the population still unbanked. Non-Banking Financial Companies (NBFCs) have emerged as key players in bridging this gap by providing financial services to those often overlooked by traditional banking institutions. This article delves into how NBFCs are fostering financial inclusion and empowering the unbanked.
when will pi network coin be available on crypto exchange.DOT TECH
There is no set date for when Pi coins will enter the market.
However, the developers are working hard to get them released as soon as possible.
Once they are available, users will be able to exchange other cryptocurrencies for Pi coins on designated exchanges.
But for now the only way to sell your pi coins is through verified pi vendor.
Here is the telegram contact of my personal pi vendor
@Pi_vendor_247
What website can I sell pi coins securely.DOT TECH
Currently there are no website or exchange that allow buying or selling of pi coins..
But you can still easily sell pi coins, by reselling it to exchanges/crypto whales interested in holding thousands of pi coins before the mainnet launch.
Who is a pi merchant?
A pi merchant is someone who buys pi coins from miners and resell to these crypto whales and holders of pi..
This is because pi network is not doing any pre-sale. The only way exchanges can get pi is by buying from miners and pi merchants stands in between the miners and the exchanges.
How can I sell my pi coins?
Selling pi coins is really easy, but first you need to migrate to mainnet wallet before you can do that. I will leave the telegram contact of my personal pi merchant to trade with.
Tele-gram.
@Pi_vendor_247
how can I sell pi coins after successfully completing KYCDOT TECH
Pi coins is not launched yet in any exchange 💱 this means it's not swappable, the current pi displaying on coin market cap is the iou version of pi. And you can learn all about that on my previous post.
RIGHT NOW THE ONLY WAY you can sell pi coins is through verified pi merchants. A pi merchant is someone who buys pi coins and resell them to exchanges and crypto whales. Looking forward to hold massive quantities of pi coins before the mainnet launch.
This is because pi network is not doing any pre-sale or ico offerings, the only way to get my coins is from buying from miners. So a merchant facilitates the transactions between the miners and these exchanges holding pi.
I and my friends has sold more than 6000 pi coins successfully with this method. I will be happy to share the contact of my personal pi merchant. The one i trade with, if you have your own merchant you can trade with them. For those who are new.
Message: @Pi_vendor_247 on telegram.
I wouldn't advise you selling all percentage of the pi coins. Leave at least a before so its a win win during open mainnet. Have a nice day pioneers ♥️
#kyc #mainnet #picoins #pi #sellpi #piwallet
#pinetwork
how to sell pi coins effectively (from 50 - 100k pi)DOT TECH
Anywhere in the world, including Africa, America, and Europe, you can sell Pi Network Coins online and receive cash through online payment options.
Pi has not yet been launched on any exchange because we are currently using the confined Mainnet. The planned launch date for Pi is June 28, 2026.
Reselling to investors who want to hold until the mainnet launch in 2026 is currently the sole way to sell.
Consequently, right now. All you need to do is select the right pi network provider.
Who is a pi merchant?
An individual who buys coins from miners on the pi network and resells them to investors hoping to hang onto them until the mainnet is launched is known as a pi merchant.
debuts.
I'll provide you the Telegram username
@Pi_vendor_247
What price will pi network be listed on exchangesDOT TECH
The rate at which pi will be listed is practically unknown. But due to speculations surrounding it the predicted rate is tends to be from 30$ — 50$.
So if you are interested in selling your pi network coins at a high rate tho. Or you can't wait till the mainnet launch in 2026. You can easily trade your pi coins with a merchant.
A merchant is someone who buys pi coins from miners and resell them to Investors looking forward to hold massive quantities till mainnet launch.
I will leave the telegram contact of my personal pi vendor to trade with.
@Pi_vendor_247
2. Introduction
Objectives
My first objective was to model housing prices at the county level using explanatory demographic variables.
My second objective was to benchmark four different models varying in complexity from simple linear regressions
to more complex Deep Neural Network (DNN) models.
Data
I used county level home price data from Zillow (“zestimates”) and I used, tested, and selected demographic
variables from the GEOFRED data in order to estimate the mentioned county-level home price zestimates.
Some of the demographic variables at GEOFRED had data on up to close to 3,150 counties. The Zillow county level
data had data on about 2,850 counties. When eliminating missing data on any of the tested variables, I ended up
with a data set of over 2,500 counties.
Variable transformation
All variables are standardized so as to be on the same scale.
Software
R neuralnet package
2
3. The selected variables
3
County level variable description (data date is most current available) Short name
Home price “zestimate”. This is the dependent Y variable we fit zillow
Personal Income in 2020 income
% of population with a 4-year college degree or higher in 2020 college
Number of patents per capita in 2015 patent
Rate of Preventable Hospital Admissions (5-year estimate) 2015 prevent
Single-Parent Households with Children as % of Households with Children (5-
year estimate) in 2020
single_parent
Homeownership rate in 2020 owner
Average commute time in minutes in 2020 commute
Population change between 2020 and 2019 pop_chg
We considered many other demographic variables at GEOFRED. But, many were missing too many county-data
points. Others were associated with correlations or regression coefficients that were either not statistically
significant or of the wrong sign. The first 7 independent variables were selected as the best ones to construct an
explanatory model. The 8th one (population change) was selected to construct a parsimonious predictive model.
4. 4
The two Linear Regression Models
OLS Long OLS Short
This is an explanatory model that captures many
socioeconomic dimensions : income, education,
innovation, behavior, single motherhood,
homeownership, and commute time.
This is a parsimonious model that generates the same
Goodness-of-fit with only 3 variables instead of 7.
Remember all the variables are standardized. So, the
regression coefficients are indicative of the relative weight
of each variable. The derived coefficients were associated
with using the entire data set.
5. 5
The two Deep Neural Network Models
DNN Soft Plus. 2 hidden layers (3, 2) DNN Logit. 2 hidden layers (4, 2)
The DNN Soft Plus uses a more advanced smooth
Rectified Linear Unit activation function called Soft
Plus (See Appendix section). It is associated with
two hidden layers. The first one with 3 neurons,
and the second one with 2 neurons.
This DNN Logit uses an older activation function:
Sigmoid. The latter is a Logit Regression. This model
structure had no problem converging towards a
solution. However, the Sigmoid activation function is
associated with coefficient compression issue when
using more than one hidden layer (See Appendix).
6. 6
DNN Soft Plus Convergence Issue
DNN Soft Plus. 2 hidden layers (3, 2)
DNN Logit. 2 hidden layers (4, 2)
For the DNN Soft Plus model to converge towards a solution,
we had to prune down the first layer from 4 neurons down
to 3. And, we also had to increase the error threshold for
the partial derivatives from 0.1 for the DNN Logit to 0.3 for the DNN Soft Plus model. As a result, when using the
whole data, the DNN Soft Plus error at 447.5 is more than twice as large as for DNN Logit (189). And, the DNN
Soft Plus needed 63% more steps (41,652 vs 25,521) to converge towards a solution.
7. 7
Fitting the entire data set. The DNN Logit model is the clear winner
The scatter plots top right
hand quadrant defined by the
red and green dashed lines
show the homes with
zestimates > $1 million.
The DNN Logit models fit the
zestimates > $1 million
perfectly. The other three
models do not fit well the > $1
million data points.
8. 8
Fitting the entire data set. The DNN Logit model is the clear winner. Part II
On all Goodness-of-fit measure, the DNN Logit model is way superior to the other three. It was expected since the DNN
Logit could exploit non-linear relationships that the OLS models could not. Also, the DNN Logit model converged towards
a solution with a much lower error than the DNN Soft Plus.
Technical notes:
When calculating the standard error, we assumed for simplicity, that each model had the same degree of freedom of 1.
Given the large sample (> 2,500), this assumption did not affect the result much. The standard error was transformed
from standardized units to nominal home values in $000.
The error reduction is calculated by comparing the standard error of the model with the standard deviation of the
dependent variable (which would be the standard error of a naïve model using the average of Y as a single estimate.
Let’s say a model has a standard error of 5, and Y has a standard deviation of 10. The error reduction = 5/10 -1 = - 50%.
9. 9
When we test the models, the DNN Logit performance is mediocre
After using the total data, we tested the
models twice using the following sample
segmentations:
a) Train 80% (learning sample) and Test
(new data) 20%;
b) Train 50%, Test 50%.
When you look at all the Goodness-of-fit
measures for the predictions in Test 20%
and Test 50%, the DNN Logit performance
falls abruptly. And, it is not any better, and
at times worse, than the other three
models.
12. 12
A closer look at the DNN Logit (80%/20%) performance
In training (80%), the model fit the data very well, including near perfect
fit of the > $1 million homes. In the test (20%) predictions, there were 3
homes near $1 million, and the model was way off on all 3.
13. 13
A closer look at the DNN Logit (50%/50%) performance
Same situation as for the 80/20 testing. The perfect fit in training on
the homes > $1 million did not help in predicting in testing similar
homes > $1 million.
14. 14
A perfect representation of overfitting … the DNN Logit model
During training, the DNN Logit model gives you the illusion that it has captured very precise non linear
relationships to perfectly fit the homes > $1 million (left graph). But, in the testing (right graph) this same
model is unable to predict similar homes > $1 million. Thus, during the training the DNN Logit model
really fit random
noise much more
than any true non
linear
relationships.
15. 15
Overfitness within OLS vs DNN models
The DNN Logit model has a much superior fit in training or when fitting using the whole data. But, is
less accurate in prediction. Again, that is a classic definition of model overfitting. It overfits on random
outliers using non linear DNN fitting capabilities that do not reflect true non linear relationships.
The OLS models have reasonably equal performance in fitting actual data vs. in predicting new data
(test). Given that, they are way less overfit than the DNN models (especially the DNN Logit one).
16. 16
For predicting home prices, OLS Short is much better than DNN Logit
OLS Short DNN Logit
With just 3 variables, the OLS Short model predicts better than the DNN Logit with 7 variables and two
hidden layers (4, 2). Also, OLS regression math is fast and closed form. DNN math is just the opposite.
17. 17
For explaining home prices, OLS Long is much better than DNN Logit
OLS Long DNN Logit
For explanatory purpose, the OLS Long model is more transparent than the DNN Logit. OLS Long allows you
to directly compare the relative weight of each sociodemographic factors. Meanwhile, the DNN Logit is
opaque. And, its complexity is associated with more random noise than true explanatory power.
18. 18
We did not speak much about the DNN Soft Plus model …
… that’s because it was neither here nor there. It pretty much replicated the
performance of the OLS models. And, it did that in the most burdensome and opaque
way possible (these characteristics are rather typical of DNNs).
In view of the above, right off the bat you would not choose it over the OLS models. By
contrast, the DNN Logit model seemed most promising in training, as it was far superior
to the other models. But, when conducting testing, it turned out that the DNN Logit was
just way overfit.
19. 19
A quick word about DNNs Activation Functions
Appendix Section
20. 20
Common DNNs Activation Functions
Until around 2017, the preferred DNN activation function was the Sigmoid or Logistic one as it had an implicit
probabilistic weight to a Yes or No loading of a node or neuron. However, soon after the Rectified Linear Unit (ReLU)
became the preferred DNN activation function. We will advance that SoftPlus, also called smooth ReLU, should be
considered a superior alternative to ReLU. See further explanation on the next slide.
21. 21
The Sigmoid or Logistic Activation Function
There is nothing wrong with the Sigmoid function per se. The problem occurs when you take the first derivative of this
function. And, it compresses the range of the values by 50% (from 0 to 1, to 0 to 0.5 for the first iteration). In iterative DNN
models, the output of one hidden layer becomes the input for the sequential layer. And, this 50% compression from one
layer to the next can generate values that converge close to zero. This problem is called the “vanishing gradient descent.”
We will see that in our situation, this problem is not material.
22. 22
ReLU and smooth ReLU or SoftPlus Activation Functions
SoftPlus appears superior to ReLu because it captures the weights of many more neurons’ features, as it does not zero
out any such features with an input value < 0. Also, it generates a continuous set of derivatives values ranging from 0 to
1. Instead, ReLu derivatives values are limited to a binomial outcome (0, 1).