Tags
AI (13)
Algebra (1)
Artificial Intelligence (4)
AWS AI Certification (1)
Back propagation (3)
Budapest (2)
Culture (2)
Differential calculus (3)
Encoding (2)
Feature Selection (2)
Forward propagation (5)
Foundation models (1)
Gradient descent (3)
Hungary (2)
language (1)
Mathematics (9)
ML (1)
Neural Network (7)
Neural Network; Machine Learning; Deep Learning; Overfitting; Underfitting; Bias; Variance; Regularization; Data Augmentation; Model Complexity; Epochs; Validation (1)
Training (3)
#12 AI Data Quality: Crap in – Crap out
AI Data Quality - Any AI project is based on data used to train the model. Unlike what we would…
#11 AI: Fixing the Training gone Wrong
Building on Paper #10’s AI training pitfalls—underfitting (too lazy), overfitting (too rigid), high bias (skewed guesses), and high variance (wild…
Sylvain LIEGE has been certified AWS Certified AI Practitioner.
We are please to share that Sylvain LIEGE has been certified by AWS as AWS Certified AI Practitioner.
#10 AI Training going wrong
This paper explores why the model might fail in practice: underfitting (too simplistic), overfitting (too rigid), and the underlying issues…
#9 AI Training & Back Propagation
AI Training & Back Propagation - In order to use a Digital Neural Network, we need to train it. In…
#8 - AI Forward Propagation
AI Forward Propagation - AI Neural networks mimic the neural network of the brain. In this paper we present what…
#7 - Artificial Intelligence : Architecture: Neural Network Design
Artificial Intelligence : Architecture: Neural Network Design - AI Neural networks mimic the neural network of the brain. Once the…
#6 - Artificial Intelligence: Digital Neural Network Architecture
Neural Network Architecture - AI Neural Networks mimic the neural network of the brain. But how do build a digital…
#5 - AI: Neural Network Principles – from Biology to Digital
AI: From Biology to Digital. AI Neural networks mimic the neural network of the brain. What are the principles driving…
#4 - AI & Mathematics: Differential Calculus
AI & Mathematics: Differential Calculus - We explore the mathematical marvels used in AI to create systems that can “predict”…
#3 - Artificial Intelligence & Mathematics: Algebra
AI Mathematics Algebra - Algebra is an essential mathematical enhancer for AI. It allows to represent the real world in…
The Most Difficult Language in Europe
A short article about Hungarian, considered the most difficult language in Europe.
Quote 9 : Minority of one
"Being a minority, even a minority of one, does not make you mad." George Orwell
Quote 8 : What Customers Really Want
"We must learn what customers really want, not what they say they want, not what we think they should want."…
Myths and Truth About Agile in Custom Software Development
Myths and Truth About Agile in Custom Software Development
Quote 7 : Good to Great
"Indeed, one of the crucial element in taking a company from good to great is somewhat paradoxical. You need executives,…
Defining the Scope of a Custom Software Development Project
Defining the Scope of a Custom Software Development Project - Capturing the Requirements is about writing down in word what…
Quote 6: Improvement is a Change
"Any improvement is a Change. Not every change is an improvement but certainly every improvement is a change." Eliyahu M.…
Software Requirements for Non-Technical Managers
Software Requirements for Non-Technical Managers - Capturing the Requirements is about writing down in word what people have in their…
Quote
Quote 3: Probabilities
Probabilities – “One winter night during one of the many German air raids on Moscow in World War II, a distinguished Soviet professor of statistics showed up in his local air-raid shelter. He had never appeared there before. “There are seven million people in Moscow”, he used to say. “Why should I expect them to hit me?” His friends were astonished to see him and asked what happened to change his mind. “Look”, he explained, “there are seven million people in Moscow and one elephant. Last night they got the elephant.” […]. /n What the professor experience really illuminates, is the dual character that runs throughout everything to do with probability: past frequencies can collide with degrees of belief when risky choices must be made.”
Peter L. Bernstein
Sylvain LIÈGE PhD.
December 2, 2024
IT for Managers
Software Architecture Explained for Non-Technical Managers
Software Architecture Explained for Non-Technical Managers – The software architecture is the master plan that combines the general software and hardware solutions to achieve the goals in respect of the global constraints.
Sylvain LIÈGE PhD.
December 2, 2024
Quote
Quote 2: Changing Ideas
“The most effective way of changing ideas is not from outside by conflict but from within by the insight rearrangement of available information.”
Edward de Bono
Sylvain LIÈGE PhD.
December 2, 2024
Quote
Quote 1: Time Pressure
“People under time pressure don’t work better; they just work faster.”
Tom DeMarco
Sylvain LIÈGE PhD.
December 2, 2024
Programming
Software Development Best Practices: Polymorphism
Polymorphism is a cornerstone of Object oriented Programming (OOP). Without mastering this concept, it is very hard to produce any quality code that will be resilient and easily testable.
This paper presents this concept with an example on how to apply it.
Sylvain LIÈGE PhD.
December 2, 2024
IT for Managers
Software Development for Non Technical Decision Makers
Essentially, converting our real life problems into software solutions is a paradigm shift. From a world of people, objects, concepts, etc., we need to move into a world that knows only one thing: manipulating numbers.
Sylvain LIÈGE PhD.
December 1, 2024
#12 AI Data Quality: Crap in – Crap out
AI Data Quality - Any AI project is based on data used to train the model. Unlike what we would imagine, getting the right data in the right shape is far from easy or obvious. Building a quality dataset is…
#11 AI: Fixing the Training gone Wrong
Building on Paper #10’s AI training pitfalls—underfitting (too lazy), overfitting (too rigid), high bias (skewed guesses), and high variance (wild swings)—this paper offers practical fixes for our smell detector. We explore three levers: boosting network capacity, extending training with more…
Sylvain LIEGE has been certified AWS Certified AI Practitioner.
We are please to share that Sylvain LIEGE has been certified by AWS as AWS Certified AI Practitioner.
#10 AI Training going wrong
This paper explores why the model might fail in practice: underfitting (too simplistic), overfitting (too rigid), and the underlying issues of bias and variance. Through examples, we show how underfitting leads to random guesses , while overfitting causes oversensitivity. We…
#9 AI Training & Back Propagation
AI Training & Back Propagation - In order to use a Digital Neural Network, we need to train it. In this paper we present how we can “train” one using supervised training and backpropagation. By comparing the model’s output with…
#8 - AI Forward Propagation
AI Forward Propagation - AI Neural networks mimic the neural network of the brain. In this paper we present what is happening inside a digital neural network from data entry to result. We study the various mathematical steps in their…
#7 - Artificial Intelligence : Architecture: Neural Network Design
Artificial Intelligence : Architecture: Neural Network Design - AI Neural networks mimic the neural network of the brain. Once the technical architecture has been built, how does each component work? We present the various mathematical component in action.
#6 - Artificial Intelligence: Digital Neural Network Architecture
Neural Network Architecture - AI Neural Networks mimic the neural network of the brain. But how do build a digital neural network? What is its architecture? We present the basic component of such technical solution.
#5 - AI: Neural Network Principles – from Biology to Digital
AI: From Biology to Digital. AI Neural networks mimic the neural network of the brain. What are the principles driving a neural network? How did we look at biology to create the most powerful “machines” ever created?
#4 - AI & Mathematics: Differential Calculus
AI & Mathematics: Differential Calculus - We explore the mathematical marvels used in AI to create systems that can “predict” the future.
#3 - Artificial Intelligence & Mathematics: Algebra
AI Mathematics Algebra - Algebra is an essential mathematical enhancer for AI. It allows to represent the real world in mathematical structures that can be easily manipulated by the computer.
The Most Difficult Language in Europe
A short article about Hungarian, considered the most difficult language in Europe.
Quote 9 : Minority of one
"Being a minority, even a minority of one, does not make you mad." George Orwell
Quote 8 : What Customers Really Want
"We must learn what customers really want, not what they say they want, not what we think they should want." Eric Ries
Myths and Truth About Agile in Custom Software Development
Myths and Truth About Agile in Custom Software Development
Quote 7 : Good to Great
"Indeed, one of the crucial element in taking a company from good to great is somewhat paradoxical. You need executives, on the one hand, who argue and debate -sometimes violently- in pursuit of best answers, yet, on the other hand,…
Defining the Scope of a Custom Software Development Project
Defining the Scope of a Custom Software Development Project - Capturing the Requirements is about writing down in word what people have in their mind.
Quote 6: Improvement is a Change
"Any improvement is a Change. Not every change is an improvement but certainly every improvement is a change." Eliyahu M. Goldratt
Software Requirements for Non-Technical Managers
Software Requirements for Non-Technical Managers - Capturing the Requirements is about writing down in word what people have in their mind.
#2 - Artificial Intelligence Origins
Artificial Intelligence Origins: If it almost never is possible and usually unfair to associate a crucial human event to only one person, it is also impossible to not name the Great Alan Turing when we think about AI.
Quote 5: Modelling
"Without modelling, we might think we are learning to think holistically when we are actually learning to jump to conclusions." Peter M. Senge
Quote 4: Bad Idea
"Both ideas and execution are important. There is no effect time way to implement a bad idea." Ronald J. Baker
#1 - The Hunt for Artificial Intelligence
The Hunt for Artificial Intelligence - AI is everywhere! There is not an industry, a service, a product that does not advertise its AI capabilities.
Quote 3: Probabilities
Probabilities - "One winter night during one of the many German air raids on Moscow in World War II, a distinguished Soviet professor of statistics showed up in his local air-raid shelter. He had never appeared there before. "There are…