7 Analysis of neural networks: a random matrix approach For a given B,the output is thus simply given by y =BT>E RaxT where >=a(wx)and the application of os activation function. During the training phase,the output weight matrix is merely learnt by solving the quadratic minimization problem B=argmingeRnxa 行y-g+呢} where y>o is some constant The solution is explicit and given by g=(宁四+)'r 88 For a given , the output is thus simply given by , where , and , and the application of is activation function. During the training phase, the output weight matrix is merely learnt by solving the quadratic minimization problem where is some constant The solution is explicit and given by 7 Analysis of neural networks: a random matrix approach