Fix: kalman_filter.py, linreg_kf.py

[gerdm]

• kalman_filter.py had an incorrect definition of self.nobs, self.nstates
• Close make Bayesian linear regression demo numerically stable #42
• Remove JSL_notebook.ipynb. Not in use

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[murphyk]

This looks clunky

b = inv(Sigma0) @ mu0 + X.T @ y / R.item()

What is R.item()? Also, I shudder when I see inv. If Sigma0 is diagonal, maybe
write jnp.diag(1/diag(Sigma0)) or something like that?

Meanwhile I will merge this so the rest of the codebase runs.