Glue (@isGLUE) header
Glue (@isGLUE) profile picture

F* the algo.

Remote
Joined June 2015
Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)Photo by Glue (@isGLUE)
1
When a machine learning model is trained on a lot of features, it becomes overfitted and more and more reliant on the training data, defeating the purpose by performing poorly on real data. Avoiding overfitting is a major motivation for performing dimensionality reduction.
2
This used to be the thing. Today all LLMs are terribly overfitted.
7
Wonderfully explained!
We keep hearing about Artificial Intelligence, Machine Learning, Neural Network, and Deep Learning. Do you know their relationship? facebook.com/groups/20594679…
1
2
But all outdated now. No vibes.
4
Glue retweeted
The Internet only tolerates complete centralization and complete decentralization. Everything in between gets destroyed.
94
314
25
3,031
357,910
1. Boosts your confidence
1
2
Know + Do, that’s how you can get the ball rolling!📈
1
5
The fewer features our training data has, the fewer assumptions our model makes and the simpler it will be. Dimensionality reduction has a lot more advantages to offer, like 1. Fewer dimensions mean less computing. Less data means that algorithms train faster.
1. AdaDelta Optimizer: It can be understood as a more robust version of the AdaGrad Optimizer. It was created to address the significant shortcomings of AdaGrad and the RMS prop optimizer and is based on adaptive learning.
RMSprop is a gradient-based optimization technique used in training neural networks. It was proposed by the father of back-propagation, Geoffrey Hinton.
1. Mini Batch Gradient Descent Optimizer: In this variation of gradient descent, only a portion of the dataset is used to calculate the loss function rather than the entire training set.
Stochastic Gradient Descent with Momentum Optimizer: We know that stochastic gradient descent takes a much more noisy path than the gradient descent algorithm.
1. Gradient Descent Optimizer: It is the most basic but most commonly used optimization algorithm. It is widely used in linear regression and classification algorithms. The gradient descent algorithm is also used in neural network backpropagation.
1
But what are multi-class classification problems? Modern machine learning problems involve complex tasks where one has to make the optimal decision given hundreds or thousands of possible actions.
It involves dividing the dataset into different and unique classes based on different parameters so that a new and unseen record can be put into one of the classes.
1
Mean Absolute Error Loss (MAE): It is defined as the #average of the absolute difference between the actual and predicted values. It is also known as the L1 loss function.
1
What are your thoughts on this Robot-CEO?🤔
AI-powered humanoid robot is the new CEO of a Chinese #metaverse company Artificial Intelligence is already threatening thousands of jobs across the world. Now, a Chinese metaverse corporation has named a robot as its CEO, a move that has people excited.
2