# Brain Bomb

Machine Learning, Deep Learning and Reinforcement Learning

##### [Neural Networks] Neuron Model and Network Architecture(Part II)

After the insight of single-input neuron, we can easily build a more complex and powerful neuron model -- multiple-inputs neuron, whose structure is more like the biological nerve cell than the single-input neuron

##### [Neural Networks] Neuron Model and Network Architecture(Part I)

We are not able to build any artificial cells up to now. It seems impossible to build a neuron network through biological materials manually, either. Then to investigate the ability of neurons we have built mathematical models of the neuron.

##### [Neural Networks] An Introduction to Neural Networks

Neural Networks are a model of our brain that is built with neurons and it is considered as the source of intelligence. There is almost $10^{11}$ neurons in the human brain and $10^4$ connections of each neuron to other neurons. Some of these brilliant structures were given when we were born. But this is not a decision for anything, such as our IQ, skills, etc. Because some other structures could be established by experience, and this progress is called learning. Learning is considered as the establishment or modification of the connections between neurons.

##### [Review] A Logical Calculus of the Ideas Immanent in Nervous Activity

This paper was published in 1943 by Warren S. McCulloch and Walter Pitts.1 It has been considered as the origin of the neural network field. It contains the background knowledge of biological neural networks of that time. Basing on these biological neural network structure details, authors discarded some "unimportant" or "uncomputable" structures and simplified some complicated structures then get an abstracted model that may have a simple function and could be analyzed mathematically.

##### [Linear Regression] Estimating Multiple Linear Regress Coefficients

An introduction of multiple linear regression

##### [Linear Regression] Assessing the Accuracy of the Model

this post talk about how to assess the accuracy of the model, and we take a linear model as an example.

##### [Linear Regression] Are the Parameters Calculated from Least Squared Error Correct?

How correct we believe the parameters of the model are always concerned by us. To have more confidence in using methods talked previously, we would like to make a reliable framework, under which the method is always feasible.

##### [Linear Regression] Simple Linear Regression

We have already created a simple linear model in the post "Introduction to Linear Regression". $y=w_1x_1+w_2x_2$ is a linear equation of both $\boldsymbol{x}=[x_1 \; x_2]^T$ and $\boldsymbol{w}=[w_1 \; w_2]^T$. According to the definition of linear, we come up with the first simplest linear regression:

##### [Linear Regression] Introduction to Linear Regression

Linear regression is a basic idea in statistical or machine learning, especially in supervises learning. The linear regression is a statistical model whose structure is based on the linear combination, and it is usually used to predict some quantitative responses to some inputs(predictors).