hi, i'm amit. currently making vitadao autonomous - shipping ai agents and other systems. driven by a passion to use technology for th...
All our lives are built on, or centered around a certain person, place or thing. It could be one's career goals, or certain ambitions, maybe even one's spouse or sometimes even one's self. When we start building our lives on these, we seldom think about the rough patches and the storms that our lives have to endure. Many a times we can pass through unchartered territories quite seamlessly, and…
As a worship leader, our goal might be to nail the Sunday morning service, make sure the congregation engages, and has their moment with the Father. Sure, that's important, but of late i've been being lead to think and ponder about the oil and anointing. It is the oil of gladness that equips you to worship in your pain and sorrow. It's the anointing that breaks the yokes and chains. None of these…
This world entices you to fulfill your cravings, desires and longings, to drench in instant dopamine hits, and drown yourself in a world full of self-seeking pleasures. We are advised to run away from evil, but what if it feels like every direction you try and run is surrounded by evil. When your spiritual eyes are opened to the routine, mundane you see things you have never seen before, you tend…
Train, validation and testing split Training data - used to train the model training error is back propagated, learning algorithms Validation data - every now and then, the interim model is tested on the validation result Validation error - wrong classification of data If you are not satisfied with the interim model then you will change the model's hyperparameters and re-train the model Q : When…
Bias and variance Reference : https://www.youtube.com/watch?v=EuBBz3bI-aA split the data into test and train ml algo = linear regression - fits a straight line to the training set - this will never capture the true relationship between the variables in the dataset the inability of an ml algo to capture the true relationship of a dataset is called BIAS here the straight line can't be curved = it…
Used to classify data if the k in knn is =1. then we only use the nearest neighbour to define the category if k=11, then we use the 11 nearest neighbors it's always easier to work with an odd value of k How to pick a value for k? Have to try out a few values of k before settling on one. Do this by pretending that a part of the training data is "unknown". low values for k can be noisy and subject…
ML goes from very abstract theory to extreme practice. Some maths in ML useful cause it gives us the conceptual framework and some practical aspects are useful cause they give us the way to deal with real learning systems. Main topics covered are : 1.What is learning? 2.Can we learn? 3. How to do it? 4. How to do it well? 5. Take home lessons. There is a logical dependency that goes through the…
Recap You can perform ML without a pattern as well Say we can pin down a mathematical function for a task - then ML is not the recommended technique, but it will still work. But we cannot perform ML without data - ML is learning from data Even though the target function is unknown, it is known on the data that will be used for training - in case of supervised learning, you have the targets…
Regression models vs classification models - Regression - deals with outputs that are continuous values - any value in the range of certain values - has discrete values Classification - deals with categorzing each result into a category Convergence - the point at which the model reaches it's optimum performance, cause even if you train the model with more data after this point, there's no point…
In the realm of MLOps (Machine Learning Operations), there are several key components to manage: model deployment, model serving, model registry, model observability, and model monitoring to name a few. Once you've completed the extensive process of testing and evaluating your machine learning model, the next step is crucial — integrating it into your workflow or scaling it to a production or…