def distribution(self, x, mean, std): """ Gaussian Distribution Function """ exponent = R.exp(-((x - mean)**2 / (2 * std**2))) gaussian_func = exponent / (R.square_root(2 * (3.1415) * std))
def distribution(self, x, mean, std): """ Gaussian Distribution Function """ numerator = R.square(x - mean) denominator = R.Scalar(2) * R.square(std) frac = R.div(numerator,denominator) exponent = R.exp(R.Scalar(-1) * frac) two_pi = R.Scalar(2) * R.pi() gaussian_denominator = R.square_root(two_pi) * std gaussian_func = R.div(exponent, gaussian_denominator) return gaussian_func
def distribution(self, x, mean, std): """ Gaussian Distribution Function exponent = np.exp(-((x-mean)**2 / (2*std**2))) gauss_func = exponent / (np.sqrt(2*np.pi)*std) """ numerator = R.square(x - mean) denominator = R.Scalar(2) * R.square(std) frac = R.div(numerator,denominator) exponent = R.exp(R.Scalar(-1) * frac) two_pi = R.Scalar(2) * R.Scalar(3.141592653589793) gaussian_denominator = R.square_root(two_pi) * std gaussian_func = R.div(exponent, gaussian_denominator) return gaussian_func
def softmax(x): """ Softmax Activation Function """ exp = R.exp(x) return R.div(exp, R.sum(exp))
def tanh(x): """ Tanh Activation Function """ return R.div(R.sub(R.exp(x), R.exp(R.mul(R.minus_one(), x))), R.add(R.exp(x), R.exp(R.mul(R.minus_one(), x))))
def sigmoid(x): """ Sigmoid Activation Function """ return R.div(R.one(), R.add(R.one(), R.exp(R.multiply(R.minus_one(), x))))
def sigmoid(x): # x is already a R.Scalar or a R.Tensor return (R.Scalar(1).div(R.Scalar(1).add(R.exp(x.multiply(R.Scalar(-1))))))
def __sigmoid(self, z): return (R.Scalar(1).div( R.Scalar(1).add(R.exp(z.multiply(R.Scalar(-1))))))