's Rushi's Ctrl+AI+Ship Home Musings Tech About Contact Tag: neural-networks Jun 02 2026 0 LLM parameters: what they are and how they actually work Posted by Rushi You’ve seen the numbers. 7B. 70B. 405B. Everyone talks about parameter counts. But what are they? Why does size matter? And what actually happens when you hit “Generate”? This post covers the mechanics: what parameters are, where they live in the model architecture, how scaling affects them, and what that means if you’re running or
# What is eszka doing ## poniedziałek, 2 stycznia 2017 ### LSTM - recurrent neural networks Since september, I was focused on my graduation project. I was working with my two friends and one of the topics was classification of data. We have to recognize gestures from data which was comming from gloves equiped with accelerometer and magnetometer sensors. There are several methods to handle that kind of problem: Dynamic Time Warping, Hidden Markov Models and neural networks. We decided to use LSTMs (Long
# Neural Networks Are Polynomial Regression Norman Matloff announces a new paper : A summary of the paper is: We present a very simple, informal mathematical argument that neural networks (NNs) are in essence polynomial regression (PR). We refer to this as NNAEPR. NNAEPR implies that we can use our knowledge of the “old-fashioned” method of PR to gain insight into how NNs — widely viewed somewhat warily as a “black box” — work inside. One such insight is that the outputs of an NN layer will be
A look at machine learning internals, and how neural networks learn and work
Dropout prevents overfitting in neural networks by introducing randomness during training, which forces the model to lea
This tutorial will show you how to implement deep learning convolutional neural networks in Python using the TensorFlow library
Recurrent Neural Networks unlock the secrets of sequence learning in AI — from speech and text to time series, discover how RNNs remember the past to predict the future
Unlocking the Secret Behind Neural Networks' Symmetry Superpowers Have you ever wondered why neural networks seem to naturally pick up on symmetries in data, even when we don't explicitly tell them to? Researchers have long observed this phenomenon, but the why behind it has remained a mystery. Now
Thomas Shultz, Professor @ McGill University Learning & development Neural networks Memory Evolution Cognitive dissonance Problem solving Decision making Commentaries Blog posts Research highlights Resolving the St. Petersburg paradox Spread of innovation in wild birds Resolving Rogers' paradox Evolution of ethnocentrism Shape of development Connectionist modeling Neural networks Symbolic modeling Causal reasoning Moral reasoning Theory of mind Development of humor LNSC Neural networks With Yoshio Takane an
General-purpose technique sheds light on inner workings of neural nets trained to process language