機械学習によく出てくるbatch_sizeとはバッチとはなんですか？

機械学習によく出てくるbatch_sizeとはバッチとはなんですか？

y_vals = np.transpose([np.array([y[13] for y in housing_data])])
x_vals = np.array([[x for i,x in enumerate(y)
                if housing_header[i] in cols_used] for y in housing_data])

#min-maxスケーリングを使って、x値を０〜１の値にスケーリング
x_vals = (x_vals - x_vals.min(0)) / x_vals.ptp(0)

np.random.seed(13)
train_indices = np.random.choice(len(x_vals), round(len(x_vals)*0.8),   replace=False)
test_indices = np.array(list(set(range(len(x_vals))) - s et(train_indices)))
x_vals_train = x_vals[train_indices]
x_vals_test = x_vals[test_indices]
y_vals_train = y_vals[train_indices]
y_vals_test = y_vals[test_indices]

k = 4
batch_size=len(x_vals_test)

参照：TensoFlow機械学習クックブック