diff --git a/src/data/roadmaps/machine-learning/content/basics-of-probability@p8q1Gtt9x19jw5_-YjAGh.md b/src/data/roadmaps/machine-learning/content/basics-of-probability@p8q1Gtt9x19jw5_-YjAGh.md index c5f9d7513..e8c8ba86c 100644 --- a/src/data/roadmaps/machine-learning/content/basics-of-probability@p8q1Gtt9x19jw5_-YjAGh.md +++ b/src/data/roadmaps/machine-learning/content/basics-of-probability@p8q1Gtt9x19jw5_-YjAGh.md @@ -4,7 +4,7 @@ Probability is a way to quantify the likelihood of an event occurring. It provid Visit the following resources to learn more: +- [@book@Probability and Statistics: The Science of Uncertainty](https://utstat.utoronto.ca/mikevans/jeffrosenthal/book.pdf) - [@article@Probability](https://en.wikipedia.org/wiki/Probability) - [@article@Probability](https://www.mathsisfun.com/data/probability.html) -- [@video@Probability Bootcamp](https://www.youtube.com/playlist?list=PLMrJAkhIeNNR3sNYvfgiKgcStwuPSts9V) -- [@book@Probability and Statistics: The Science of Uncertainty](https://utstat.utoronto.ca/mikevans/jeffrosenthal/book.pdf) \ No newline at end of file +- [@video@Probability Bootcamp](https://www.youtube.com/playlist?list=PLMrJAkhIeNNR3sNYvfgiKgcStwuPSts9V) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/calculus@wHlEinHuRARp5OfSulpA-.md b/src/data/roadmaps/machine-learning/content/calculus@wHlEinHuRARp5OfSulpA-.md index 1b1ed13ff..3cfc8d231 100644 --- a/src/data/roadmaps/machine-learning/content/calculus@wHlEinHuRARp5OfSulpA-.md +++ b/src/data/roadmaps/machine-learning/content/calculus@wHlEinHuRARp5OfSulpA-.md @@ -4,6 +4,6 @@ Calculus is a branch of mathematics that deals with continuous change. It provid Visit the following resources to learn more: -- [@article@Calculus](https://en.wikipedia.org/wiki/Calculus) - [@book@Calculus Online Textbook](https://ocw.mit.edu/courses/res-18-001-calculus-fall-2023/pages/textbook/) +- [@article@Calculus](https://en.wikipedia.org/wiki/Calculus) - [@video@Calculus](https://www.youtube.com/playlist?list=PLybg94GvOJ9ELZEe9s2NXTKr41Yedbw7M) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/chain-rule-of-derivation@jJukG4XxfFcID_VlQKqe-.md b/src/data/roadmaps/machine-learning/content/chain-rule-of-derivation@jJukG4XxfFcID_VlQKqe-.md index 69076b894..6e615dcc5 100644 --- a/src/data/roadmaps/machine-learning/content/chain-rule-of-derivation@jJukG4XxfFcID_VlQKqe-.md +++ b/src/data/roadmaps/machine-learning/content/chain-rule-of-derivation@jJukG4XxfFcID_VlQKqe-.md @@ -1,6 +1,6 @@ # Chain Rule of Derivation -The chain rule is a formula for finding the derivative of a composite function. If you have a function that's made up of one function inside another (like sin(x²) ), the chain rule lets you break down the differentiation process. It states that the derivative of the composite function is the derivative of the outer function evaluated at the inner function, multiplied by the derivative of the inner function. +The chain rule is a formula for finding the derivative of a composite function. If you have a function that's made up of one function inside another (like sin(x²) ), the chain rule lets you break down the differentiation process. It states that the derivative of the composite function is the derivative of the outer function evaluated at the inner function, multiplied by the derivative of the inner function. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/classification@cffITx6oAcnvJlK1VLdi8.md b/src/data/roadmaps/machine-learning/content/classification@cffITx6oAcnvJlK1VLdi8.md index 35b5f58d0..218a57e4f 100644 --- a/src/data/roadmaps/machine-learning/content/classification@cffITx6oAcnvJlK1VLdi8.md +++ b/src/data/roadmaps/machine-learning/content/classification@cffITx6oAcnvJlK1VLdi8.md @@ -4,6 +4,6 @@ Classification is a type of supervised learning where the goal is to assign data Visit the following resources to learn more: +- [@course@Classification - Google Crash Course](https://developers.google.com/machine-learning/crash-course/classification) - [@article@What is Classification in Machine Learning?](https://www.ibm.com/think/topics/classification-machine-learning) -- [@article@Classification in Machine Learning: A Guide for Beginners](https://www.datacamp.com/blog/classification-machine-learning) -- [@course@Classification - Google Crash Course](https://developers.google.com/machine-learning/crash-course/classification) \ No newline at end of file +- [@article@Classification in Machine Learning: A Guide for Beginners](https://www.datacamp.com/blog/classification-machine-learning) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/conditionals@NP1kjSk0ujU0Gx-ajNHlR.md b/src/data/roadmaps/machine-learning/content/conditionals@NP1kjSk0ujU0Gx-ajNHlR.md index 1e50afe13..4dae1e69a 100644 --- a/src/data/roadmaps/machine-learning/content/conditionals@NP1kjSk0ujU0Gx-ajNHlR.md +++ b/src/data/roadmaps/machine-learning/content/conditionals@NP1kjSk0ujU0Gx-ajNHlR.md @@ -1,6 +1,6 @@ # Conditionals -Conditional statements in Python allow you to execute different blocks of code based on whether a certain condition is true or false. The most common conditional statements are `if`, `elif` (else if), and `else`. An `if` statement checks a condition, and if it's true, the code block under it runs. `elif` allows you to check additional conditions if the initial `if` condition is false. Finally, `else` provides a block of code to execute if none of the preceding `if` or `elif` conditions are true. These statements enable programs to make decisions and respond differently to various inputs or situations. +Conditional statements in Python allow you to execute different blocks of code based on whether a certain condition is true or false. The most common conditional statements are `if`, `elif` (else if), and `else`. An `if` statement checks a condition, and if it's true, the code block under it runs. `elif` allows you to check additional conditions if the initial `if` condition is false. Finally, `else` provides a block of code to execute if none of the preceding `if` or `elif` conditions are true. These statements enable programs to make decisions and respond differently to various inputs or situations. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/convolution@MtoYStcZBduLSbjRuPjq0.md b/src/data/roadmaps/machine-learning/content/convolution@MtoYStcZBduLSbjRuPjq0.md index ed8528b9c..019d53b9d 100644 --- a/src/data/roadmaps/machine-learning/content/convolution@MtoYStcZBduLSbjRuPjq0.md +++ b/src/data/roadmaps/machine-learning/content/convolution@MtoYStcZBduLSbjRuPjq0.md @@ -1,6 +1,6 @@ # Convolution -Convolution is a mathematical operation that involves sliding a filter (also known as a kernel) over an input image or feature map. At each location, the filter performs element-wise multiplication with the corresponding part of the input, and then sums the results. This sum becomes a single value in the output feature map. By sliding the filter across the entire input, the convolution operation extracts features and patterns present in the image, such as edges, textures, or shapes. +Convolution is a mathematical operation that involves sliding a filter (also known as a kernel) over an input image or feature map. At each location, the filter performs element-wise multiplication with the corresponding part of the input, and then sums the results. This sum becomes a single value in the output feature map. By sliding the filter across the entire input, the convolution operation extracts features and patterns present in the image, such as edges, textures, or shapes. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/deep-q-networks@9o-ZT9oZIE3hCXD6eWZI0.md b/src/data/roadmaps/machine-learning/content/deep-q-networks@9o-ZT9oZIE3hCXD6eWZI0.md index 2ef87e35e..c5978c935 100644 --- a/src/data/roadmaps/machine-learning/content/deep-q-networks@9o-ZT9oZIE3hCXD6eWZI0.md +++ b/src/data/roadmaps/machine-learning/content/deep-q-networks@9o-ZT9oZIE3hCXD6eWZI0.md @@ -1,6 +1,6 @@ # Deep Q-Networks (DQN) -Deep Q-Networks (DQNs) are a type of reinforcement learning algorithm that combines Q-learning with deep neural networks. Instead of using a traditional Q-table to store Q-values (which represent the expected reward for taking a specific action in a specific state), DQNs use a neural network to approximate the Q-function. This allows DQNs to handle environments with large or continuous state spaces where a Q-table would be impractical. The neural network takes the state as input and outputs the Q-values for each possible action, enabling the agent to learn optimal policies through trial and error. +Deep Q-Networks (DQNs) are a type of reinforcement learning algorithm that combines Q-learning with deep neural networks. Instead of using a traditional Q-table to store Q-values (which represent the expected reward for taking a specific action in a specific state), DQNs use a neural network to approximate the Q-function. This allows DQNs to handle environments with large or continuous state spaces where a Q-table would be impractical. The neural network takes the state as input and outputs the Q-values for each possible action, enabling the agent to learn optimal policies through trial and error. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/eigenvalues-diagonalization@3p98Uwf8gyALDr-89lBEZ.md b/src/data/roadmaps/machine-learning/content/eigenvalues-diagonalization@3p98Uwf8gyALDr-89lBEZ.md index 56ce30b5d..aaad5d6a0 100644 --- a/src/data/roadmaps/machine-learning/content/eigenvalues-diagonalization@3p98Uwf8gyALDr-89lBEZ.md +++ b/src/data/roadmaps/machine-learning/content/eigenvalues-diagonalization@3p98Uwf8gyALDr-89lBEZ.md @@ -5,6 +5,6 @@ Eigenvalues are special numbers associated with a square matrix that, when multi Visit the following resources to learn more: - [@article@Eigenvalues and eigenvectors](https://en.wikipedia.org/wiki/Eigenvalues_and_eigenvectors) -- [@video@Finding Eigenvalues and Eigenvectors](https://www.youtube.com/watch?v=TQvxWaQnrqI) - [@article@Matrix Diagonalization](https://www.statlect.com/matrix-algebra/matrix-diagonalization) +- [@video@Finding Eigenvalues and Eigenvectors](https://www.youtube.com/watch?v=TQvxWaQnrqI) - [@video@Diagonalization](https://www.youtube.com/watch?v=WTLl03D4TNA) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/generative-adversarial-networks@IR0wVIcu1MxOOBiLBnn8S.md b/src/data/roadmaps/machine-learning/content/generative-adversarial-networks@IR0wVIcu1MxOOBiLBnn8S.md index 064789a7d..c815d94f3 100644 --- a/src/data/roadmaps/machine-learning/content/generative-adversarial-networks@IR0wVIcu1MxOOBiLBnn8S.md +++ b/src/data/roadmaps/machine-learning/content/generative-adversarial-networks@IR0wVIcu1MxOOBiLBnn8S.md @@ -4,7 +4,7 @@ Generative Adversarial Networks (GANs) are a type of neural network architecture Visit the following resources to learn more: +- [@course@GANs | Google](https://developers.google.com/machine-learning/gan) - [@article@What is a GAN? | AWS](https://aws.amazon.com/what-is/gan/) - [@article@Generative Adversarial Networks | HuggingFace](https://huggingface.co/learn/computer-vision-course/en/unit5/generative-models/gans) -- [@course@GANs | Google](https://developers.google.com/machine-learning/gan) - [@video@What are GANs (Generative Adversarial Networks)?](https://www.youtube.com/watch?v=TpMIssRdhco) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/iot@KeGCHoJRHp-mBX-P5to4Y.md b/src/data/roadmaps/machine-learning/content/iot@KeGCHoJRHp-mBX-P5to4Y.md index 94be066ba..67e559b0f 100644 --- a/src/data/roadmaps/machine-learning/content/iot@KeGCHoJRHp-mBX-P5to4Y.md +++ b/src/data/roadmaps/machine-learning/content/iot@KeGCHoJRHp-mBX-P5to4Y.md @@ -2,9 +2,9 @@ The Internet of Things (IoT) refers to the network of physical devices, vehicles, home appliances, and other items embedded with electronics, software, sensors, and actuators that enable these objects to connect and exchange data. These devices continuously generate vast amounts of data reflecting their status, environment, and interactions. This data can include sensor readings like temperature, pressure, humidity, location, and images or video streams. -- [@article@What is the Internet of Things (IoT)?](https://www.ibm.com/think/topics/internet-of-things) -- [@article@Internet of Things](https://en.wikipedia.org/wiki/Internet_of_things) -- [@video@What is IoT (Internet of Things)? An Introduction](https://www.youtube.com/watch?v=4FxU-xpuCww) +* [@article@What is the Internet of Things (IoT)?](https://www.ibm.com/think/topics/internet-of-things) +* [@article@Internet of Things](https://en.wikipedia.org/wiki/Internet_of_things) +* [@video@What is IoT (Internet of Things)? An Introduction](https://www.youtube.com/watch?v=4FxU-xpuCww) Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/k-fold-cross-validation@vRS7DW2WUaXiHk9oJgg3z.md b/src/data/roadmaps/machine-learning/content/k-fold-cross-validation@vRS7DW2WUaXiHk9oJgg3z.md index b933f4426..48a842f26 100644 --- a/src/data/roadmaps/machine-learning/content/k-fold-cross-validation@vRS7DW2WUaXiHk9oJgg3z.md +++ b/src/data/roadmaps/machine-learning/content/k-fold-cross-validation@vRS7DW2WUaXiHk9oJgg3z.md @@ -1,6 +1,6 @@ # K-Fold Cross Validation -K-Fold Cross Validation is a technique used to assess how well a machine learning model will generalize to an independent dataset. It works by dividing the available data into *k* equally sized folds or subsets. The model is then trained *k* times, each time using *k-1* folds as the training set and the remaining fold as the validation set. The performance metrics from each of the *k* iterations are then averaged to provide an overall estimate of the model's performance. +K-Fold Cross Validation is a technique used to assess how well a machine learning model will generalize to an independent dataset. It works by dividing the available data into _k_ equally sized folds or subsets. The model is then trained _k_ times, each time using _k-1_ folds as the training set and the remaining fold as the validation set. The performance metrics from each of the _k_ iterations are then averaged to provide an overall estimate of the model's performance. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/keras@zoXnXI4Wf5sxddHqYwQjP.md b/src/data/roadmaps/machine-learning/content/keras@zoXnXI4Wf5sxddHqYwQjP.md index 201eeabe5..6ed99bd4b 100644 --- a/src/data/roadmaps/machine-learning/content/keras@zoXnXI4Wf5sxddHqYwQjP.md +++ b/src/data/roadmaps/machine-learning/content/keras@zoXnXI4Wf5sxddHqYwQjP.md @@ -4,7 +4,7 @@ Keras is a high-level, user-friendly neural networks API written in Python. It a Visit the following resources to learn more: +- [@course@Getting Familiar with Keras](https://towardsdatascience.com/getting-familiar-with-keras-dd17a110652d/) - [@official@Keras](https://keras.io/) - [@opensource@Keras](https://github.com/keras-team/keras) -- [@course@Getting Familiar with Keras](https://towardsdatascience.com/getting-familiar-with-keras-dd17a110652d/) - [@article@Keras Crash Course | Deep Learning, Image Modelling, RNNs and More](https://www.youtube.com/watch?v=a8op1jBG7oM) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/linear-algebra@83UDoO1vC0LjL-qpI0Jh-.md b/src/data/roadmaps/machine-learning/content/linear-algebra@83UDoO1vC0LjL-qpI0Jh-.md index ccc208067..a687b4787 100644 --- a/src/data/roadmaps/machine-learning/content/linear-algebra@83UDoO1vC0LjL-qpI0Jh-.md +++ b/src/data/roadmaps/machine-learning/content/linear-algebra@83UDoO1vC0LjL-qpI0Jh-.md @@ -4,6 +4,6 @@ Linear algebra is a branch of mathematics that deals with vector spaces and line Visit the following resources to learn more: +- [@book@Linear algebra for data science](http://mitran-lab.amath.unc.edu/courses/MATH347DS/textbook.pdf) - [@article@How I learned Linear Algebra, Probability and Statistics for Data Science](https://towardsdatascience.com/how-i-learned-linear-algebra-probability-and-statistics-for-data-science-b9d1c34dfa56/) -- [@video@Linear Algebra for Machine Learning](https://www.youtube.com/watch?v=QCPJ0VdpM00) -- [@book@Linear algebra for data science](http://mitran-lab.amath.unc.edu/courses/MATH347DS/textbook.pdf) \ No newline at end of file +- [@video@Linear Algebra for Machine Learning](https://www.youtube.com/watch?v=QCPJ0VdpM00) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/natural-language-processing@JVXe2QDQaqiJYPupIMhWe.md b/src/data/roadmaps/machine-learning/content/natural-language-processing@JVXe2QDQaqiJYPupIMhWe.md index d0b4664b3..469f53209 100644 --- a/src/data/roadmaps/machine-learning/content/natural-language-processing@JVXe2QDQaqiJYPupIMhWe.md +++ b/src/data/roadmaps/machine-learning/content/natural-language-processing@JVXe2QDQaqiJYPupIMhWe.md @@ -4,7 +4,7 @@ Natural Language Processing (NLP) is a field focused on enabling computers to un Visit the following resources to learn more: +- [@book@Natural Language Processing with Python](https://tjzhifei.github.io/resources/NLTK.pdf) - [@article@Natural Language Processing](https://www.deeplearning.ai/resources/natural-language-processing/) - [@article@What is Natural Language Processing (NLP)? | AWS](https://aws.amazon.com/what-is/nlp/) -- [@video@Stanford’s Natural Language Processing with Deep Learning](https://www.youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4) -- [@book@Natural Language Processing with Python](https://tjzhifei.github.io/resources/NLTK.pdf) \ No newline at end of file +- [@video@Stanford’s Natural Language Processing with Deep Learning](https://www.youtube.com/playlist?list=PLoROMvodv4rMFqRtEuo6SGjY4XbRIVRd4) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/neural-network-nn-basics@4dxZmLg0UEaaVEORupOOC.md b/src/data/roadmaps/machine-learning/content/neural-network-nn-basics@4dxZmLg0UEaaVEORupOOC.md index feadcd3cf..c3b41e4a4 100644 --- a/src/data/roadmaps/machine-learning/content/neural-network-nn-basics@4dxZmLg0UEaaVEORupOOC.md +++ b/src/data/roadmaps/machine-learning/content/neural-network-nn-basics@4dxZmLg0UEaaVEORupOOC.md @@ -4,5 +4,5 @@ A neural network is a computational model inspired by the structure and function Visit the following resources to learn more: -- [@video@Neural Networks Explained in 5 minutes](https://www.youtube.com/watch?v=jmmW0F0biz0) -- [@course@Practical Deep Learning](https://course.fast.ai/) \ No newline at end of file +- [@course@Practical Deep Learning](https://course.fast.ai/) +- [@video@Neural Networks Explained in 5 minutes](https://www.youtube.com/watch?v=jmmW0F0biz0) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/object-oriented-programming@nN9BumBHi-c9HKFlgL2GH.md b/src/data/roadmaps/machine-learning/content/object-oriented-programming@nN9BumBHi-c9HKFlgL2GH.md index 3417ec59f..1f6f62036 100644 --- a/src/data/roadmaps/machine-learning/content/object-oriented-programming@nN9BumBHi-c9HKFlgL2GH.md +++ b/src/data/roadmaps/machine-learning/content/object-oriented-programming@nN9BumBHi-c9HKFlgL2GH.md @@ -5,6 +5,6 @@ In Python, object-oriented Programming (OOPs) is a programming paradigm that use Visit the following resources to learn more: - [@article@Object Oriented Programming in Python](https://realpython.com/python3-object-oriented-programming/) +- [@article@https://www.youtube.com/watch?v=Ej_02ICOIgs](https://www.youtube.com/watch?v=Ej_02ICOIgs) - [@video@Object Oriented Programming (OOP) In Python - Beginner Crash Course](https://www.youtube.com/watch?v=-pEs-Bss8Wc/) -- [@video@OOP in Python One Shot]](https://www.youtube.com/watch?v=Ej_02ICOIgs) - [@video@Python OOP Tutorial](https://www.youtube.com/watch?v=IbMDCwVm63M) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/overlapping@BzUunjJrUMlh6K1NOOD87.md b/src/data/roadmaps/machine-learning/content/overlapping@BzUunjJrUMlh6K1NOOD87.md index 01a84ca69..8e7c85388 100644 --- a/src/data/roadmaps/machine-learning/content/overlapping@BzUunjJrUMlh6K1NOOD87.md +++ b/src/data/roadmaps/machine-learning/content/overlapping@BzUunjJrUMlh6K1NOOD87.md @@ -1,6 +1,6 @@ # Overlapping Clustering -Overlapping clustering allows data points to belong to multiple clusters simultaneously. Unlike traditional "hard" clustering where each point is assigned to only one cluster, overlapping clustering acknowledges that data points can exhibit characteristics of several groups. This is particularly useful when dealing with complex datasets where boundaries between clusters are not well-defined. One algorithm that implements overlapping clustering is the *Fuzzy C-Means (FCM)* algorithm. FCM assigns a membership degree to each data point for each cluster, representing the probability of belonging to that cluster. A data point can have non-zero membership degrees for multiple clusters, indicating its partial membership in each. +Overlapping clustering allows data points to belong to multiple clusters simultaneously. Unlike traditional "hard" clustering where each point is assigned to only one cluster, overlapping clustering acknowledges that data points can exhibit characteristics of several groups. This is particularly useful when dealing with complex datasets where boundaries between clusters are not well-defined. One algorithm that implements overlapping clustering is the _Fuzzy C-Means (FCM)_ algorithm. FCM assigns a membership degree to each data point for each cluster, representing the probability of belonging to that cluster. A data point can have non-zero membership degrees for multiple clusters, indicating its partial membership in each. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/probability@tP0oBkjvJC9hrtARkgLon.md b/src/data/roadmaps/machine-learning/content/probability@tP0oBkjvJC9hrtARkgLon.md index ccc208067..a687b4787 100644 --- a/src/data/roadmaps/machine-learning/content/probability@tP0oBkjvJC9hrtARkgLon.md +++ b/src/data/roadmaps/machine-learning/content/probability@tP0oBkjvJC9hrtARkgLon.md @@ -4,6 +4,6 @@ Linear algebra is a branch of mathematics that deals with vector spaces and line Visit the following resources to learn more: +- [@book@Linear algebra for data science](http://mitran-lab.amath.unc.edu/courses/MATH347DS/textbook.pdf) - [@article@How I learned Linear Algebra, Probability and Statistics for Data Science](https://towardsdatascience.com/how-i-learned-linear-algebra-probability-and-statistics-for-data-science-b9d1c34dfa56/) -- [@video@Linear Algebra for Machine Learning](https://www.youtube.com/watch?v=QCPJ0VdpM00) -- [@book@Linear algebra for data science](http://mitran-lab.amath.unc.edu/courses/MATH347DS/textbook.pdf) \ No newline at end of file +- [@video@Linear Algebra for Machine Learning](https://www.youtube.com/watch?v=QCPJ0VdpM00) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/random-variances-pdfs@P576TdYcbE6v3RpJntiKw.md b/src/data/roadmaps/machine-learning/content/random-variances-pdfs@P576TdYcbE6v3RpJntiKw.md index bc3206b4a..79d69400d 100644 --- a/src/data/roadmaps/machine-learning/content/random-variances-pdfs@P576TdYcbE6v3RpJntiKw.md +++ b/src/data/roadmaps/machine-learning/content/random-variances-pdfs@P576TdYcbE6v3RpJntiKw.md @@ -1,6 +1,6 @@ # Random Variables and Probability Density Functions -A random variable is a variable whose value is a numerical outcome of a random phenomenon. It can be discrete (taking on a finite or countably infinite number of values) or continuous (taking on any value within a given range). +A random variable is a variable whose value is a numerical outcome of a random phenomenon. It can be discrete (taking on a finite or countably infinite number of values) or continuous (taking on any value within a given range). The probability density function (PDF) describes the relative likelihood for a continuous random variable to take on a given value. It's important to note that the value of the PDF at any given point is not a probability itself, but rather the area under the PDF curve over a given interval represents the probability of the random variable falling within that interval. diff --git a/src/data/roadmaps/machine-learning/content/recall@DH33Na9zz_WGmbD-Dxvq1.md b/src/data/roadmaps/machine-learning/content/recall@DH33Na9zz_WGmbD-Dxvq1.md index 48dab6291..0de682214 100644 --- a/src/data/roadmaps/machine-learning/content/recall@DH33Na9zz_WGmbD-Dxvq1.md +++ b/src/data/roadmaps/machine-learning/content/recall@DH33Na9zz_WGmbD-Dxvq1.md @@ -1,6 +1,6 @@ # Recall -Recall measures how well a model identifies all the actual positive cases. It answers the question: "Of all the actual positive instances, how many did the model correctly predict as positive?". A high recall means the model is good at minimizing false negatives. The formula for recall is: `Recall = True Positives / (True Positives + False Negatives)`. +Recall measures how well a model identifies all the actual positive cases. It answers the question: "Of all the actual positive instances, how many did the model correctly predict as positive?". A high recall means the model is good at minimizing false negatives. The formula for recall is: `Recall = True Positives / (True Positives + False Negatives)`. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/reinforcement-learning@NC1A2SQVyc1n-KEf6yl-4.md b/src/data/roadmaps/machine-learning/content/reinforcement-learning@NC1A2SQVyc1n-KEf6yl-4.md index 289c987bb..5e8573955 100644 --- a/src/data/roadmaps/machine-learning/content/reinforcement-learning@NC1A2SQVyc1n-KEf6yl-4.md +++ b/src/data/roadmaps/machine-learning/content/reinforcement-learning@NC1A2SQVyc1n-KEf6yl-4.md @@ -6,5 +6,5 @@ Visit the following resources to learn more: - [@article@What is reinforcement learning?](https://online.york.ac.uk/resources/what-is-reinforcement-learning/) - [@article@Resources to Learn Reinforcement Learning](https://towardsdatascience.com/best-free-courses-and-resources-to-learn-reinforcement-learning-ed6633608cb2/) -- [@course@Deep Reinforcement Learning Course by HuggingFace]](https://huggingface.co/learn/deep-rl-course/unit0/introduction) +- [@article@https://huggingface.co/learn/deep-rl-course/unit0/introduction](https://huggingface.co/learn/deep-rl-course/unit0/introduction) - [@article@Reinforcement Learning in 3 Hours | Full Course using Python](https://www.youtube.com/watch?v=Mut_u40Sqz4) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/semi-supervised-learning@Yho0zf9F-ROhEnTxRMq_M.md b/src/data/roadmaps/machine-learning/content/semi-supervised-learning@Yho0zf9F-ROhEnTxRMq_M.md index bc2549bc2..a28592679 100644 --- a/src/data/roadmaps/machine-learning/content/semi-supervised-learning@Yho0zf9F-ROhEnTxRMq_M.md +++ b/src/data/roadmaps/machine-learning/content/semi-supervised-learning@Yho0zf9F-ROhEnTxRMq_M.md @@ -1,6 +1,6 @@ # Semi-Supervised Learning -Semi-supervised learning is a type of machine learning where the training data contains both labeled and unlabeled examples. The goal is to leverage the information from the unlabeled data to improve the performance of a model that would otherwise be trained solely on the labeled data. This approach is particularly useful when obtaining labels is expensive or time-consuming, but unlabeled data is readily available. +Semi-supervised learning is a type of machine learning where the training data contains both labeled and unlabeled examples. The goal is to leverage the information from the unlabeled data to improve the performance of a model that would otherwise be trained solely on the labeled data. This approach is particularly useful when obtaining labels is expensive or time-consuming, but unlabeled data is readily available. Visit the following resources to learn more: diff --git a/src/data/roadmaps/machine-learning/content/singular-value-decomposition@yGs2h10gZcO4GMaWfI3uW.md b/src/data/roadmaps/machine-learning/content/singular-value-decomposition@yGs2h10gZcO4GMaWfI3uW.md index f43e91293..d7596fee5 100644 --- a/src/data/roadmaps/machine-learning/content/singular-value-decomposition@yGs2h10gZcO4GMaWfI3uW.md +++ b/src/data/roadmaps/machine-learning/content/singular-value-decomposition@yGs2h10gZcO4GMaWfI3uW.md @@ -4,6 +4,6 @@ Singular Value Decomposition (SVD) is a matrix factorization technique that deco Visit the following resources to learn more: +- [@book@Singular Value Decomposition](https://www.cs.cmu.edu/~venkatg/teaching/CStheory-infoage/book-chapter-4.pdf) - [@article@Singular Value Decomposition](https://en.wikipedia.org/wiki/Singular_value_decomposition) -- [@video@Singular Value Decomposition (SVD): Overview](https://www.youtube.com/watch?v=gXbThCXjZFM) -- [@book@Singular Value Decomposition](https://www.cs.cmu.edu/~venkatg/teaching/CStheory-infoage/book-chapter-4.pdf) \ No newline at end of file +- [@video@Singular Value Decomposition (SVD): Overview](https://www.youtube.com/watch?v=gXbThCXjZFM) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/statistics@5DiaZkljhHAGPi9DkaH3b.md b/src/data/roadmaps/machine-learning/content/statistics@5DiaZkljhHAGPi9DkaH3b.md index ca1002f1d..d013831cd 100644 --- a/src/data/roadmaps/machine-learning/content/statistics@5DiaZkljhHAGPi9DkaH3b.md +++ b/src/data/roadmaps/machine-learning/content/statistics@5DiaZkljhHAGPi9DkaH3b.md @@ -4,6 +4,6 @@ Statistics is the science of collecting, analyzing, interpreting, presenting, an Visit the following resources to learn more: -- [@article@Introduction to Statistics](https://imp.i384100.net/3eRv4v) - [@book@Introductory Statistics](https://assets.openstax.org/oscms-prodcms/media/documents/IntroductoryStatistics-OP_i6tAI7e.pdf) +- [@article@Introduction to Statistics](https://imp.i384100.net/3eRv4v) - [@video@Statistics - A Full University Course on Data Science Basics](https://www.youtube.com/watch?v=xxpc-HPKN28) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/transformers@rDIg16eb6B6um1P8uMy51.md b/src/data/roadmaps/machine-learning/content/transformers@rDIg16eb6B6um1P8uMy51.md index 901232a82..7044374b6 100644 --- a/src/data/roadmaps/machine-learning/content/transformers@rDIg16eb6B6um1P8uMy51.md +++ b/src/data/roadmaps/machine-learning/content/transformers@rDIg16eb6B6um1P8uMy51.md @@ -4,7 +4,7 @@ Transformers are a type of neural network architecture that rely on attention me Visit the following resources to learn more: +- [@course@LLM Course | HuggingFace](https://huggingface.co/learn/llm-course/chapter1/1) - [@article@What is a Transformer Model?](https://www.ibm.com/think/topics/transformer-model) - [@article@How Transformers Work: A Detailed Exploration of Transformer Architecture](https://www.datacamp.com/tutorial/how-transformers-work) -- [@course@LLM Course | HuggingFace](https://huggingface.co/learn/llm-course/chapter1/1) - [@video@Transformers, explained: Understand the model behind GPT, BERT, and T5](https://www.youtube.com/watch?v=SZorAJ4I-sA&t) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/what-is-machine-learning@rzhVFzl5H5MWtcvr8ayRk.md b/src/data/roadmaps/machine-learning/content/what-is-machine-learning@rzhVFzl5H5MWtcvr8ayRk.md index cfeec51f9..f5e1d109d 100644 --- a/src/data/roadmaps/machine-learning/content/what-is-machine-learning@rzhVFzl5H5MWtcvr8ayRk.md +++ b/src/data/roadmaps/machine-learning/content/what-is-machine-learning@rzhVFzl5H5MWtcvr8ayRk.md @@ -4,7 +4,7 @@ Machine learning is a field of computer science that focuses on enabling compute Visit the following resources to learn more: +- [@book@Machine Learning: The Basics](https://alexjungaalto.github.io/MLBasicsBook.pdf) - [@article@What is Machine Learning (ML)?](https://www.ibm.com/topics/machine-learning) - [@video@What is Machine Learning?](https://www.youtube.com/watch?v=9gGnTQTYNaE) -- [@video@Complete Machine Learning in One Video | Machine Learning Tutorial For Beginners 2025 | Simplilearn](https://www.youtube.com/watch?v=PtYRUoJRE9s) -- [@book@Machine Learning: The Basics](https://alexjungaalto.github.io/MLBasicsBook.pdf) \ No newline at end of file +- [@video@Complete Machine Learning in One Video | Machine Learning Tutorial For Beginners 2025 | Simplilearn](https://www.youtube.com/watch?v=PtYRUoJRE9s) \ No newline at end of file diff --git a/src/data/roadmaps/machine-learning/content/what-is-reinforcement-learning@EtU_9MOklVBvnvyg30Yfx.md b/src/data/roadmaps/machine-learning/content/what-is-reinforcement-learning@EtU_9MOklVBvnvyg30Yfx.md index ab93ce9f6..7d415574c 100644 --- a/src/data/roadmaps/machine-learning/content/what-is-reinforcement-learning@EtU_9MOklVBvnvyg30Yfx.md +++ b/src/data/roadmaps/machine-learning/content/what-is-reinforcement-learning@EtU_9MOklVBvnvyg30Yfx.md @@ -6,5 +6,5 @@ Visit the following resources to learn more: - [@article@What is reinforcement learning?](https://online.york.ac.uk/resources/what-is-reinforcement-learning/) - [@article@Resources to Learn Reinforcement Learning](https://towardsdatascience.com/best-free-courses-and-resources-to-learn-reinforcement-learning-ed6633608cb2/) -- [@course@Deep Reinforcement Learning Course by HuggingFace]](https://huggingface.co/learn/deep-rl-course/unit0/introduction) +- [@article@https://huggingface.co/learn/deep-rl-course/unit0/introduction](https://huggingface.co/learn/deep-rl-course/unit0/introduction) - [@video@Reinforcement Learning in 3 Hours | Full Course using Python](https://www.youtube.com/watch?v=Mut_u40Sqz4) \ No newline at end of file